GPT-5.6 Terra: score and benchmark evidence
Historical release · · OpenAI
95.1 points · Rank 12 among 19 ranked models · Stability range 88.8–101.3 points.
Rank follows the point estimate; it does not establish statistically significant superiority. The scale is anchored at mean 100, SD 15 in the frozen calibration cohort, not human IQ or a percentage.
One score summarizes demonstrated capability across published reasoning settings and seven equally weighted domains. Related benchmark variants share a family budget, and influence from one evaluator is capped.
Release tli-2026-v1.0-2026-09-06-presentation-1. Methodology and limitations for this release.
This page preserves historical evidence. See the current model record.
Capability domains
Domain scores use calibration-cohort standard-deviation units. Unmeasured domains are shown as unavailable, not zero.
| Domain | Score (SD units) | Observed benchmarks |
|---|---|---|
| Knowledge & reasoning | -0.12 | 13 |
| Coding & software engineering | -0.12 | 13 |
| Agentic tool & computer use | 0.12 | 6 |
| Professional & real-world work | -0.23 | 14 |
| Multimodal & vision | -0.29 | 5 |
| Cybersecurity | Unavailable | 0 |
| Preference & communication | -0.21 | 3 |
Published benchmark evidence
54 results contribute to this score, from 80 collected results and 50 contributing benchmark families. Counts are not independent sample sizes.
Results, source citations, review decisions and compatible reasoning modes are stored in a versioned relational database. Each publication uses a sealed, checksum-verified export; CSV files are optional exports, not editable scoring inputs. Previous revisions remain available for audit. Collected means a numeric result exists in the database. Used means its source, exact model checkpoint and benchmark protocol have been reviewed and its benchmark has a frozen calibration supported by multiple providers. For each benchmark we select the highest published aggregate across comparable reasoning modes, not necessarily maximum effort, and count it once. More tested settings provide more chances to record a high score; this selection advantage is not corrected by the conditional interval. Developer-reported and sole/unspecified settings remain eligible and disclosed. Unresolved does not mean false or useless: conflicting metrics, unverified citations and unmatched versions stay collected until reconciled.
The score stability range is a 95% bootstrap score interval conditional on frozen calibration and comparable evidence availability. It resamples benchmark families and evaluators and adds a frozen missing-evidence correction. It excludes selection across reasoning settings, selective publication, calibration changes and new domains. It is not a 95% guarantee about true capability or where a future score will land. Sparse or conflicting evidence can widen the range.
Reporting sensitivity: ±1.2 points. Sensitivity to selectively published results. This stress range is not a confidence interval or a probability statement.
GDPval-AA v2 (Elo): 1482.49 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (xhigh); Artificial Analysis published evaluation harness
Metric: Elo
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
Terminal-Bench 2.1: 88.014981%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: pass@1, AA harness
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
DeepSWE v1.1: 69.62306%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: gpt-5-6-terra; max; mini-swe-agent
Metric: pass@1 over scored rollout attempts
Original source · Retrieved 2026-09-06
Selected the best pass@1 across published reasoning efforts within mini-swe-agent. Pass@4 is not substituted.
LMArena (Chatbot Arena) — Text: 1466.420286 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: gpt-5.6-terra-xhigh; Arena text overall; style control enabled
Metric: style-controlled text overall Elo
Original source · Retrieved 2026-09-06
Best published reasoning-mode rating within the same text overall board. Different leaderboard slices and undated earlier DeepSeek checkpoints are not pooled.
AA Intelligence Index v4.1.1 (score): 57 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
GPQA Diamond: 92.525253%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
AA-LCR: 79.7%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: GPT-5.6 Terra (max)
Original source · Retrieved 2026-09-06
Current AA result is LCR v1.1. The inherited AA-LCR row has no reviewed version match; a new version cannot silently substantiate the older value.
Finance Agent v2 — Vals: 54.44%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: fabv2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Excel Modeling Benchmark — Vals: 66.2%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: emb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SciCode: 54.976852%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: accuracy, AA harness
Original source · Retrieved 2026-09-06
Best published result among 3 reasoning configurations of the exact AA model release; fallback configurations excluded.
Humanity's Last Exam (no tools): 42.910102%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: accuracy, no tools, AA
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
Legal Research Bench — Vals: 41.35%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: legal_research overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Harvey LAB (Vals): 0.83%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: hlab overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AA-Briefcase Overall Elo: 1341.29 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (xhigh); Artificial Analysis published evaluation harness
Metric: overall Elo
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
MedScribe — Vals: 82.87%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: medscribe overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SWE-bench Verified — Vals: 95.4%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: swebench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LegalBench — Vals: 85.11%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: legal_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
TaxEval v2 — Vals: 76.17%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: tax_eval_v2 overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
KingBench 3: 62.9%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 62.9 for GPT-5.6 Terra on KingBench 3 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Vals Index: 56.53%
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
Public Benefits Bench — Vals: 62.38%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: public-benefits-bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
MedCode — Vals: 43.41%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: medcode overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
AutomationBench v1.0.6: 37.17%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 37.17 for GPT-5.6 Terra on AutomationBench v1.0.6 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
AA-Omniscience: 0.05 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: knowledge reliability index -100 to 100
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
MMLU Pro — Vals: 86.66%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: mmlu_pro overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LiveBench: 77.93625%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: gpt-5.6-terra-max; LiveBench 2026-06-25 release
Metric: official overall: equal mean of seven category means
Original source · Retrieved 2026-09-06
Task mapping archived from categories_2026_06_25.json. Aggregate follows the official UI, not a flat mean of the 23 tasks. Undated old DeepSeek checkpoints excluded.
CorpFin v2 — Vals: 65.31%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 65.31 for GPT-5.6 Terra on CorpFin v2 — Vals still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
MortgageTax — Vals: 67.33%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: mortgage_tax overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SAGE — Vals: 47%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: sage overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Code Migration †: 47.8%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: code-migration overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Toolathlon-Verified: 74.9%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 74.9 for GPT-5.6 Terra on Toolathlon-Verified still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Agents' Last Exam: 28%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra; Max; Codex
Metric: pass rate, ALE-V1 147 tasks; not partial score
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Terminal-Bench v3.0: 20.8%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Codex
Metric: resolution rate on v3.0 task set
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
LiveCodeBench: 85.93%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: lcb overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
CyberGym: 81.8%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 81.8 for GPT-5.6 Terra on CyberGym still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Design Arena (Elo): 1280 native-points
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 1280 for GPT-5.6 Terra on Design Arena (Elo) still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
Vals Multimodal Index: 65.07%
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
SWE-Marathon v1.1: 32.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 32.5 for GPT-5.6 Terra on SWE-Marathon v1.1 still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
ProgramBench v1 (Raw Pass Rate) — Vals: 72.345%
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: openai/gpt-5.6-terra · reasoning_effort=max
Metric: Raw Pass Rate: mean percent of hidden behavioral tests passed per task. Not Fully Resolved (all tests pass) and not Almost Resolved (≥95% of tests pass).
Original source · Retrieved 2026-09-05
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
SkillsBench †: 58.9%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: skillsbench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
FrontierMath v2 Tier 4: 70.731707%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: gpt-5.6-terra_max; task version 2.0.0
Metric: mean score percentage, FrontierMath-Tier-4-v2-Private
Original source · Retrieved 2026-09-06
Exact Epoch task version; selected best mean score across reported reasoning configurations. No pooling of task versions or substitution of best scorer output.
CursorBench v3.2: 64.9%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra Max; Cursor harness
Metric: CursorBench 3.2 score percentage
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
SWE-bench Pro: 63.4%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 63.4 for GPT-5.6 Terra on SWE-bench Pro still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
CharXiv (with CI / RQ): 88%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 88 for GPT-5.6 Terra on CharXiv (with CI / RQ) still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
BrowseComp: 87.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 87.5 for GPT-5.6 Terra on BrowseComp still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
MMMU-Pro: 80.693642%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
ARC-AGI-2: 83.9%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra; Max; ARC Prize standard harness
Metric: semi-private verified score percentage
Original source · Retrieved 2026-09-06
Best reasoning variant within the verified standard-harness summary. Provider Adapter, public tasks and community agent scores are not substituted.
OSWorld 2.0 — Anthropic H2H: 50.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 50.2 for GPT-5.6 Terra on OSWorld 2.0 — Anthropic H2H still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
ExploitBench: 52.9%
Not used in the score. Source category not recorded. Review status: excluded.
Inherited comparator metric/scaffold equivalence to Astra Cap Percent is not established; the source flags possible contamination. Excluded pending protocol audit.
SimpleQA: 43.1%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 43.1 for GPT-5.6 Terra on SimpleQA still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
FrontierCode v1.1 Extended: 55.84%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra; max; codex
Metric: v1.1 Extended cost-adjusted new_score, 150 tasks
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Creative Writing v3: 1850 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: gpt-5.6-terra; published evaluation, effort unspecified
Metric: Creative Writing v3 Elo
Original source · Retrieved 2026-09-06
Exact checkpoint on the evaluator-hosted board. A starred model is externally submitted; it is not claimed as independently rerun by the benchmark owner.
AIIQ Composite IQ: 132 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
EQ-Bench 4: 1234 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai/gpt-5.6-terra; evaluator published configuration, effort unspecified
Metric: EQ-Bench 4 Elo
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
τ²-Bench Telecom: 86.3%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 86.3 for GPT-5.6 Terra on τ²-Bench Telecom still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
FrontierCode v1.1 Main — Anthropic H2H: 41.3%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 41.3 for GPT-5.6 Terra on FrontierCode v1.1 Main — Anthropic H2H still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
τ³-Banking: 40.206186%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: strict task success, AA
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
CritPt: 30%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: accuracy, AA official grading
Original source · Retrieved 2026-09-06
Best published result among 6 reasoning configurations of the exact AA model release; fallback configurations excluded.
Terminal-Bench 4.0: 21.5%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra; max; Codex
Metric: resolution rate, v4.0.0 66 tasks
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
GDP.pdf: 24.7%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (Medium reasoning); Surge original evaluation
Metric: all-pass percentage, original Surge GDP.pdf
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
ProofBench v1.1 — Vals: 74%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: proof_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Vibe Code Bench v1.1 — Vals: 74.59%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: vibe-code overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
ARC-AGI-1: 96.5%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra; Max; ARC Prize standard harness
Metric: semi-private verified score percentage
Original source · Retrieved 2026-09-06
Best reasoning variant within the verified standard-harness summary. Provider Adapter, public tasks and community agent scores are not substituted.
ARC-AGI-3 (standard harness): 0.8%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra; Max; ARC Prize standard harness
Metric: semi-private verified score percentage
Original source · Retrieved 2026-09-06
Best reasoning variant within the verified standard-harness summary. Provider Adapter, public tasks and community agent scores are not substituted.
HealthBench: 58.7%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: GPT-5.6 Terra; OpenAI published HealthBench research evaluation; effort unspecified
Metric: raw physician rubric score, not length-adjusted
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
HealthBench Hard: 34.3%
Not used in the score. Developer-reported. Review status: reviewed-developer.
Configuration: GPT-5.6 Terra; OpenAI published HealthBench research evaluation; effort unspecified
Metric: raw physician rubric score, not length-adjusted
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
HealthBench Professional (length-adjusted): 57.7%
Not used in the score. Source category not recorded. Review status: unresolved.
Source selects the maximum score across efforts; exact highest-effort result is not established.
Harvey LAB-AA: 85.18%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 85.18 for GPT-5.6 Terra on Harvey LAB-AA still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
EnterpriseOps-Gym-AA: 38.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 38.5 for GPT-5.6 Terra on EnterpriseOps-Gym-AA still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
MLCR-AA (Medical Long Context Reasoning): 31.666667%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: overall accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 5 reasoning configurations of the exact AA model release; fallback configurations excluded.
ITBench-AA: 51.035782%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); Artificial Analysis published evaluation harness
Metric: root cause accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
Vending-Bench 2: 7343.206 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra; Andon Labs Vending-Bench 2
Metric: arithmetic mean final bank balance USD after one simulated year
Original source · Retrieved 2026-09-06
Compare reasoning configurations using their mean over runs. Geometric mean, individual best runs, Fireworks Kimi endpoint, Vending Arena, and April DeepSeek Pro are not substituted.
IFBench: 71.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 71.2 for GPT-5.6 Terra on IFBench still lacks a matched source entry establishing its checkpoint and benchmark-specific metric, tools and retry setup. This is a citation/comparability gap, not a finding that the result is false or useless. More or maximum reasoning effort is not required.
ZeroBench: 19%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: GPT-5.6 Terra (max); official main questions
Metric: pass@5, 100 main questions, no tools, August 2026 grading
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
Mystery Game Puzzles v1.0.4 — Epoch: 35%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: gpt-5.6-terra_max; task version 1.0.4
Metric: mean score percentage, Mystery Game Puzzles
Original source · Retrieved 2026-09-06
Exact Epoch task version; selected best mean score across reported reasoning configurations. No pooling of task versions or substitution of best scorer output.
Tax Agent Bench v1 — Vals: 65.2%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: openai_gpt-5.6-terra; Vals max effort
Metric: tax_agent_bench overall percentage in Vals benchmark harness
Original source · Retrieved 2026-09-06
Reconciled against the exact model/configuration in the evaluator’s public source. Updated source value recorded explicitly; best published reasoning mode selected within the same benchmark protocol.
RuneBench (30m, mean ln(1 + XP/min)): 5.881388 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: gpt56terra-xhigh
Metric: Arithmetic mean of ln(1 + peakXpRate) over all 16 skills, exactly as the owner’s Heatmap.js default ranking. Data rates are already normalized; do not divide by 200 again.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
VoxelBench (text-to-voxel, Glicko-2): 1963 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: GPT-5.6-Terra
Metric: Glicko-2 rating from the text-to-voxel board; not win percentage, deviation, image-input mode or MineBench Elo.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Roboflow Vision Evals (six-task mean, high tier): 74.25%
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: Require a complete six-task high-tier panel, the highest published benchmark tier. Retain high-tier scores even when lower than low-tier. Do not substitute the best of three repetitions: use the published mean. Each panel enters the fit once; do not also fit its components.
Metric: Arithmetic mean of six published high-tier task means; derived by The Latent, not Roboflow’s official low-tier overall score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Code Arena WebDev (overall): 1520 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: gpt-5.6-terra-xhigh (codex-harness)
Metric: Published overall WebDev preference rating, not task success percentage or Arena Text score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Cite this model record
The Latent. “GPT-5.6 Terra: score and benchmark evidence.” 2026-09-06. Release tli-2026-v1.0-2026-09-06-presentation-1.
Download release data and definitions (JSON) · Data usage terms