LabsDeepSeek
DeepSeek
Track DeepSeek model scores across public AI benchmarks including GPQA Diamond, AAII, GDPval-AA, SciCode, and EQ-Bench Creative v3. Each result is shown one benchmark at a time, with source links and evaluation dates — no blended score or composite ranking. 7 models tracked, spanning DeepSeek, DeepSeek V3, and DeepSeek-V4.
Models 7
DeepSeek V4 Flash
DeepSeek-V4 · deepseek v4 flash
2026-04-24
17 results
DeepSeek V4 Pro
DeepSeek · deepseek-v4-pro
2026-04-24
25 results
DeepSeek V3.2
DeepSeek · deepseek-v3.2
2025-12-01
31 results
DeepSeek V3.1
DeepSeek V3 · deepseek v3.1
2025-08-21
20 results
DeepSeek V3 0324
DeepSeek · deepseek-v3-0324
2025-03-24
15 results
DeepSeek R1
DeepSeek · deepseek r1
2025-01-20
29 results
DeepSeek V3
DeepSeek · deepseek v3
2024-12-26
15 results
Progress by benchmark
Show progress on
Single benchmark only
This view shows GPQA Diamond (accuracy) only. Other benchmarks use different metrics and are not directly comparable.
Progress matrix
| Model | SWE-bench Verified % resolved | Terminal-Bench 2.1 task success | DeepSWE % resolved | GPQA Diamond accuracy | LiveCodeBench Pro Codeforces Elo | Humanity's Last Exam accuracy | LiveBench score | SWE-bench Pro % resolved | Berkeley Function Calling Leaderboard accuracy | MMMU-Pro accuracy | LMArena source-defined rating | ARC-AGI-1 accuracy | ARC-AGI-2 accuracy | ARC-AGI-3 accuracy | FrontierMath accuracy | AIME (OTIS Mock) accuracy | SimpleQA Verified accuracy | GBA Eval overall score | WeirdML average accuracy | MCP Atlas pass rate | Remote Labor Index automation rate | Artificial Analysis Intelligence Index Index | Epoch Capabilities Index Index | Aider Polyglot % correct | SWE-rebench Resolved rate (pass@1) | MMLU-Pro accuracy | OSWorld task success rate | GAIA: A Benchmark for General AI Assistants accuracy | BrowseComp accuracy | τ²-bench (Telecom) pass^1 | AIME 2026 accuracy | MathVista accuracy | Video-MME accuracy | GDPval Elo | LiveCodeBench Pass@1 | METR Task-Completion Time Horizons 50% time horizon | SciCode accuracy | MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark) accuracy | AA-Omniscience: Knowledge and Hallucination Benchmark AA-Omniscience Index | IFBench accuracy | MultiChallenge accuracy | OpenAI-MRCR v2 (Multi-Round Coreference Resolution) accuracy (mean SequenceMatcher similarity) | LongBench v2 accuracy | Global-MMLU accuracy | Video-MMMU accuracy | WebDev Arena Elo | Search Arena Elo | Arena-Hard-Auto v2.0 % win rate | EQ-Bench Creative Writing v3 Elo | Design Arena Elo | AILuminate AI Safety Benchmark Safety grade | MASK (Model Alignment between Statements and Knowledge) Honesty score | MCP-Universe Overall Success Rate | CharXiv accuracy | OCRBench v2 accuracy | ScreenSpot-Pro accuracy | FACTS Grounding Grounding accuracy | BigCodeBench calibrated Pass@1 | SWE-bench Multilingual % resolved | SWE-bench Multimodal % resolved | SuperGPQA accuracy | EnigmaEval accuracy | ZeroBench accuracy | IMO-Bench accuracy | PutnamBench Problems solved | MathArena HMMT February 2026 accuracy | FrontierMath Tier 4 accuracy | Vectara Hallucination Leaderboard Hallucination Rate | Gray Swan Arena (Agent Red-Teaming / Indirect Prompt Injection) Attack Success Rate (ASR) | PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts Difficulty-Weighted Accuracy (DW-ACC) | Vibe Code Bench Overall accuracy | Online-Mind2Web Task success rate | WebArena Task success rate | GSO: Software Optimization Benchmark for SWE-Agents Opt@1 | MultiNRC accuracy | Terminal-Bench 2.0 task success | SWE-Marathon resolution rate (pass@1) | FrontierCode weighted score (Diamond) | FrontierSWE dominance score | ProgramBench almost-resolved rate | CursorBench score | PostTrainBench weighted average score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3 DeepSeek | — | — | — | 56.5% | — | — | — | — | — | — | 1332 | — | — | — | 1.72% | 15.8% | — | — | — | — | — | 16.5 | 133.1 | — | — | 75.9% | — | 29.39% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 14.29% | — | — | — | — | 40.5% | — | — | 47.40% | — | — | 37.0% | — | — | — | 6.1% | — | 20.4 | — | 32.33% | — | — | — | — | — | — | — | — | — | — |
| DeepSeek R1 DeepSeek | — | — | — | 69.2% | 1284 | 8.5% | — | — | — | — | 1372 | — | — | — | — | 53.3% | — | — | 36.5% | — | — | 27.1 | 142.2 | 71.4% | — | 84.9% | — | 30.30% | — | — | — | — | — | 248 | 61.7% | — | 35.7% | — | — | 38.0% | — | — | 58.3% | 86.0% | — | — | — | 58.0% | 1500 | 1193 | — | 57.32 | — | — | — | — | — | 40.5% | — | — | 61.82% | — | — | 60.8% | 1 | — | — | 11.3% | — | 47.0 | — | 25.33% | — | — | 24.27% | — | — | — | — | — | — | — |
| DeepSeek V3 0324 DeepSeek | — | — | — | — | 1124 | — | — | — | — | — | 1374 | — | — | — | — | — | — | — | 36.1% | — | — | — | 137.2 | 55.1% | — | 81.9% | — | — | — | — | — | — | — | 407 | 40.5% | — | 35.8% | — | — | — | — | — | — | — | — | — | — | — | 1474 | 1163 | — | 44.53 | — | — | — | — | — | 35.8% | — | — | — | — | — | — | 0 | — | — | — | — | 30.7 | — | — | — | — | — | — | — | — | — | — | — | — |
| DeepSeek V3.1 DeepSeek V3 | 66.0% | — | — | 80.1% | — | 15.9% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.1 | 138.9 | 68.4% | — | 85.1% | — | 11.5% | — | — | — | — | — | 1080 | 57.7% | — | 36.7% | — | — | — | 46.10% | — | — | 82.7% | — | — | — | — | 1420 | 1166 | — | 46.27 | 22.08% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 5.5% | 5.4% | — | — | — | — | — | 23.60% | — | — | — | — | — | — | — |
| DeepSeek V3.2 DeepSeek | — | — | — | 83.4% | — | — | — | 15.56% | 56.73% | — | 1423 | 57% | 4.03% | — | 22.1% | 87.8% | 27.5% | — | 39.5% | — | — | 32 | 146.5 | 74.2% | 60.9% | 86.2% | — | 34.8% | 40.1% | — | 94.17% | — | — | 1197 | 59.3% | — | 38.7% | — | — | — | — | — | — | 86.5% | — | 1332 | — | — | 1515 | 1220 | — | — | 19.91% | — | — | — | — | — | 59.0% | — | — | — | — | — | — | 84.09% | 2.1% | 6.3% | — | — | — | — | — | — | — | 39.6% | — | — | — | — | — | — |
| DeepSeek V4 Pro DeepSeek | 80.6% | — | 5.3% | 90.1% | 3206 | 32.4% | 73.58% | 55.4% | — | — | 1446 | — | — | — | — | — | — | — | 48.9% | — | — | 51.5 | — | — | — | — | — | — | — | 96.2% | 95.83% | — | — | 1558 | — | — | 50.0% | — | -10 | 76.5% | — | — | — | — | — | 1464 | — | — | 1570 | 1302 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 93.94% | — | 8.6% | — | — | 49.93% | — | — | — | — | 67.9% | — | — | 29% | — | — | — |
| DeepSeek V4 Flash DeepSeek-V4 | 79.0% | — | — | 88.1% | — | 34.8% | — | 52.6% | — | — | — | — | — | — | — | — | 34.1% | — | — | 69.0% | — | 46.5 | — | — | — | — | — | — | — | 95.0% | 95.83% | — | — | 1414 | — | — | 44.9% | — | -23 | 79.2% | — | — | — | — | — | — | — | — | 1556 | 1268 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 93.94% | — | — | — | — | — | — | — | — | — | 56.9% | — | — | — | — | — | — |
Scores are not normalised across benchmarks. Each column uses its own metric. Compare columns independently.