DeepSeek
availableShows if the model has enough results for an index.DeepSeek V3.1
DeepSeek V3.1 is a non-reasoning model from DeepSeek. 10 benchmarks count toward its score, in 4 categories.
IndexOverall score out of 100.37.7 ±9.6
CoverageShare of the index weight with results.55%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.1420 (#110)
The index is a score out of 100. The ± range shows how much it can change.
14,607 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
10 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Artificial Analysis GPQA Diamond | Knowledge | 73.5% | 43.9 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 47.0% | 40.8 | — | — | Artificial Analysis |
| Terminal-Bench 1.0 | Agentic | 41.3% | 46.5 | — | 12 Jan 2026 | Vals AI |
| Artificial Analysis IFBench | Instruction | 37.8% | 27.5 | — | — | Artificial Analysis |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 34.8% | 23.8 | — | — | Victor Barres et al. |
| Artificial Analysis Omniscience Accuracy | Knowledge | 23.1% | 42.4 | — | — | Artificial Analysis |
| Terminal-Bench 2.0 | Agentic | 22.5% | 38.7 | — | 4 Jun 2026 | Vals AI |
| Artificial Analysis Intelligence Index | Knowledge | 13.7% | 39.5 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 6.7% | 31.8 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
10 benchmarks count, from 10 of 10 results. A grey row does not count. Too few models took that benchmark.