DeepSeek
availableShows if the model has enough results for an index.DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 is a model from DeepSeek. 27 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.62.4 ±4.6
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.33/s
Input / 1MUS dollars per 1M input tokens.$0.955
Output / 1MUS dollars per 1M output tokens.$1.91
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.1451 (#43)
50 is the middle of the board. The range shows the doubt in the index.
54,130 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
27 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | Math | 96.7% | 65.6 | max effort | — | Epoch AI |
| LiveBench Mathematics | Math | 92.9% | 72.0 | — | 25 Jun 2026 | LiveBench |
| GPQA Diamond | Knowledge | 90.9% | 62.2 | — | 1 Sept 2026 | Vals AI |
| GPQA diamond | Knowledge | 89.6% | 61.0 | max effort | — | Epoch AI |
| LiveCodeBench | Coding | 87.5% | 63.9 | — | 1 Sept 2026 | Vals AI |
| MMLU Pro | Knowledge | 87.1% | 57.8 | — | 1 Sept 2026 | Vals AI |
| SWE-bench | Coding | 86.9% | 67.2 | — | 1 Sept 2026 | Vals AI |
| LiveBench Reasoning | Reasoning | 84.3% | 73.0 | — | 25 Jun 2026 | LiveBench |
| LiveBench Language | Knowledge | 80.1% | 67.2 | — | 25 Jun 2026 | LiveBench |
| SWE-Bench verified | Coding | 77.6% | 59.8 | max effort | — | Epoch AI |
| LiveBench Data Analysis | Reasoning | 76.9% | 62.8 | — | 25 Jun 2026 | LiveBench |
| LiveBench Coding | Coding | 73.6% | 59.8 | — | 25 Jun 2026 | LiveBench |
| Vibe Code Bench v1.1 | Coding | 66.1% | 69.7 | OpenHands | 21 Sept 2026 | Vals AI |
| LiveBench Instruction Following | Instruction | 65.0% | 62.7 | — | 25 Jun 2026 | LiveBench |
| Terminal-Bench 2.0 | Agentic | 56.2% | 62.8 | — | 4 Jun 2026 | Vals AI |
| SkillsBench | Coding | 52.6% | 67.5 | OpenHands | 11 Sept 2026 | Vals AI |
| Terminal-Bench 2.1 | Agentic | 52.4% | 55.0 | — | 21 Sept 2026 | Vals AI |
| IOI | Coding | 51.6% | 68.1 | — | 21 Sept 2026 | Vals AI |
| LiveBench Agentic Coding | Agentic | 48.8% | 62.6 | — | 25 Jun 2026 | LiveBench |
| SimpleQA Verified | Knowledge | 47.0% | 65.1 | max effort | — | Epoch AI |
| FrontierMath-Tiers-1-3-v2-Private | Math | 45.3% | 56.9 | max effort | — | Epoch AI |
| IOI v1 | Coding | 35.8% | 60.3 | — | 9 Aug 2026 | Vals AI |
| Code Migration | Coding | 33.9% | 66.6 | — | 21 Sept 2026 | Vals AI |
| ProofBench v1.1 | Math | 33.0% | 62.8 | — | 21 Sept 2026 | Vals AI |
| Chess Puzzles | Reasoning | 20.0% | 49.4 | max effort | — | Epoch AI |
| Vibe Code Bench 1-100 | Coding | 17.5% | 71.0 | OpenHands | 16 Sept 2026 | Vals AI |
| Mystery Game Puzzles | Reasoning | 17.0% | 52.0 | none effort | — | Epoch AI |
| Agent Arena command recovery | Agentic | 3.2 | 70.9 | — | 15 Sept 2026 | LMArena |
| FrontierMath-Tier-4-v2-Private | Math | 2.4% | 49.1 | max effort | — | Epoch AI |
| Terminal-Bench 4.0 | Agentic | 1.0% | 60.2 | — | 21 Sept 2026 | Vals AI |
| ProgramBench | Coding | 0.0% | — | — | 21 Sept 2026 | Vals AI |
| Agent Arena task outcome | Agentic | -1.7 | 65.4 | — | 15 Sept 2026 | LMArena |
| Agent Arena steerability | Agentic | -2.1 | 65.0 | — | 15 Sept 2026 | LMArena |
27 benchmarks count, from 32 of 33 results. A grey row does not count. Too few models took that benchmark.