DeepSeek
availableShows if the model has enough results for an index.DeepSeek V3.2 (Thinking)
DeepSeek V3.2 (Thinking) is a reasoning model from DeepSeek in the DeepSeek V3.2 family. 9 benchmarks count toward its score, in 4 categories.
IndexOverall score out of 100.49.9 ±8.9
CoverageShare of the index weight with results.65%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.$0.55
Output / 1MUS dollars per 1M output tokens.$2.19
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
9 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. |
|---|---|---|---|---|---|---|
| MGSM | Multilingual | 86.0% | — | — | 9 Jan 2026 | Vals AI |
| MMLU Pro | Knowledge | 84.9% | 54.3 | — | 1 Sept 2026 | Vals AI |
| AIME | Math | 84.6% | 53.2 | — | 16 Apr 2026 | Vals AI |
| LiveCodeBench | Coding | 80.7% | 57.7 | — | 1 Sept 2026 | Vals AI |
| GPQA Diamond | Knowledge | 80.3% | 52.4 | — | 1 Sept 2026 | Vals AI |
| SWE-bench | Coding | 67.6% | 51.8 | — | 1 Sept 2026 | Vals AI |
| Terminal-Bench 1.0 | Agentic | 40.0% | 45.4 | — | 12 Jan 2026 | Vals AI |
| Terminal-Bench 2.0 | Agentic | 36.0% | 48.3 | — | 4 Jun 2026 | Vals AI |
| IOI v1 | Coding | 10.7% | 46.0 | — | 9 Aug 2026 | Vals AI |
| Vibe Code Bench v1.1 | Coding | 5.1% | 44.3 | OpenHands | 21 Sept 2026 | Vals AI |
9 benchmarks count, from 9 of 10 results. A grey row does not count. Too few models took that benchmark.