DeepSeek V4 Flash: score and benchmark evidence
Historical release · · DeepSeek
67.2 points · Rank 19 among 19 ranked models · Stability range 59.6–74 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-v1.0-2026-09-10-benchmarks-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 | -0.89 | 10 |
| Coding & software engineering | -0.84 | 9 |
| Agentic tool & computer use | -0.77 | 5 |
| Professional & real-world work | -0.96 | 10 |
| Multimodal & vision | -0.97 | 1 |
| Cybersecurity | -0.87 | 1 |
| Preference & communication | -1.00 | 1 |
Published benchmark evidence
37 results contribute to this score, from 57 collected results and 36 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: ±1.4 points. Sensitivity to selectively published results. This stress range is not a confidence interval or a probability statement.
GDPval-AA v2 (Elo): 1580.66 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash Vision (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: Elo
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
Terminal-Bench 2.1: 78.651685%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: pass@1, AA harness
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
DeepSWE v1.1: 53.318584%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek-v4-flash; 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: 1435 native-points
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 1435 for DeepSeek V4 Flash on LMArena (Chatbot Arena) — Text 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 Intelligence Index v4.1.1 (score): 52 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
GPQA Diamond: 91.313131%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash Vision (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
AA-LCR: 66%
Not used in the score. Source category: independent. Review status: unresolved.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
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: 49.52%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 56.98%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 50.347222%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: accuracy, AA harness
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
Humanity's Last Exam (no tools): 38.554217%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: accuracy, no tools, AA
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
Legal Research Bench — Vals: 30.29%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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): 8.33%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 1262.58 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: overall Elo
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
MedScribe — Vals: 80.36%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 88.8%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 77.71%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 70.69%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 72.5%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 72.5 for DeepSeek V4 Flash 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: 53.57%
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
MedCode — Vals: 41.41%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 25.1%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 25.1 for DeepSeek V4 Flash 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: -14.283333 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: knowledge reliability index -100 to 100
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
MMLU Pro — Vals: 86.21%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 74.170786%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek-v4-flash-0731; 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: 61.85%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 61.85 for DeepSeek V4 Flash 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.
Code Migration †: 38.63%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 70.7%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (max) ✓; Default agent
Metric: pass@1, verified 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.
Agents' Last Exam: 25.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 25.2 for DeepSeek V4 Flash on Agents' Last Exam 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.
LiveCodeBench: 87.26%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 76.7%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 76.7 for DeepSeek V4 Flash 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.
Humanity's Last Exam w/ tools: 45.1%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 45.1 for DeepSeek V4 Flash on Humanity's Last Exam w/ tools 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.
SkillsBench †: 50.67%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 24.4%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 24.4 for DeepSeek V4 Flash on FrontierMath v2 Tier 4 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.
APEX-Agents Mean Criteria Passed: 51.6%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek-v4-flash; max; loop_truncated_tools_agent
Metric: mean-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.
SWE-bench Pro: 52.6%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 52.6 for DeepSeek V4 Flash 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.
APEX-SWE (Pass@1, Terminus-2): 46.9%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek-v4-flash; max; terminus-2
Metric: pass-1
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.
BrowseComp: 73.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 73.2 for DeepSeek V4 Flash 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.
ARC-AGI-2: 61.4%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash; 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.
FrontierCode v1.1 Extended: 31.7%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731; high; chisel
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: 1438.3 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: *deepseek-ai/DeepSeek-V4-Flash-0731; 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.
MathArena — ArXivMath Jun 2026: 42.86%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 42.86 for DeepSeek V4 Flash on MathArena — ArXivMath Jun 2026 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.
MathArena — BrokenArXiv Jun 2026: 16.67%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 16.67 for DeepSeek V4 Flash on MathArena — BrokenArXiv Jun 2026 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.
NL2Repo: 54.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 54.2 for DeepSeek V4 Flash on NL2Repo 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.
MathArena — ArXivMath May 2026: 55.83%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 55.83 for DeepSeek V4 Flash on MathArena — ArXivMath May 2026 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.
EQ-Bench 3: 1491.3 native-points
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 1491.3 for DeepSeek V4 Flash on EQ-Bench 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.
τ³-Banking: 41.030928%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash Vision (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: strict task success, AA
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
CritPt: 16.571429%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: accuracy, AA official grading
Original source · Retrieved 2026-09-06
Best published result among 2 reasoning configurations of the exact AA model release; fallback configurations excluded.
ProofBench v1.1 — Vals: 56%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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: 74.74%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: deepseek_deepseek-v4-flash-0731; Vals high 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.
MineBench: 1601 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Unresolved Pro/base model identities in source catalog; exclude until matched.
ARC-AGI-1: 89%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash; 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.
MLCR-AA (Medical Long Context Reasoning): 13.333333%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash 0731 (Reasoning, Max Effort); Artificial Analysis published evaluation harness
Metric: overall accuracy, AA
Original source · Retrieved 2026-09-06
Best published result among 1 reasoning configurations of the exact AA model release; fallback configurations excluded.
CWE-bench: 30.4%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: DeepSeek V4 Flash; high; opencode
Metric: pass@1, 100 held-out audit-and-patch 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.
Mystery Game Puzzles v1.0.4 — Epoch: 34%
Not used in the score. Source category not recorded. Review status: unresolved.
Not admitted after the September 6 model review: the collected 34 for DeepSeek V4 Flash on Mystery Game Puzzles v1.0.4 — Epoch 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.
RuneBench (30m, mean ln(1 + XP/min)): 4.195298 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: deepseekflash0731
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): 1436 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: DeepSeek V4 Flash (July 2026)
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.
Cite this model record
The Latent. “DeepSeek V4 Flash: score and benchmark evidence.” 2026-09-10. Release tli-2026-v1.0-2026-09-10-benchmarks-1.
Download release data and definitions (JSON) · Data usage terms