Anthropic
availableShows if the model has enough results for an index.Claude Sonnet 4.5 Thinking
Claude Sonnet 4.5 Thinking is a reasoning model from Anthropic in the Claude Sonnet 4.5 family. 11 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.56.1 ±6.9
CoverageShare of the index weight with results.80%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.200K
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
11 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 | 94.3% | — | — | 9 Jan 2026 | Vals AI |
| AIME | Math | 88.2% | 54.8 | — | 16 Apr 2026 | Vals AI |
| MMLU Pro | Knowledge | 87.4% | 58.2 | — | 1 Sept 2026 | Vals AI |
| GPQA Diamond | Knowledge | 81.6% | 53.6 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 79.3% | 56.4 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 73.0% | 50.7 | — | 1 Sept 2026 | Vals AI |
| SWE-bench | Coding | 70.0% | 53.7 | — | 1 Sept 2026 | Vals AI |
| EuroEval French | Multilingual | 66.9% | 85.8 | thinking effort | — | EuroEval |
| EuroEval Swedish | Multilingual | 66.0% | 84.7 | thinking effort | — | EuroEval |
| EuroEval Dutch | Multilingual | 65.3% | 83.8 | thinking effort | — | EuroEval |
| EuroEval Italian | Multilingual | 65.1% | 83.6 | thinking effort | — | EuroEval |
| EuroEval Portuguese | Multilingual | 64.8% | 83.2 | thinking effort | — | EuroEval |
| EuroEval Polish | Multilingual | 63.8% | 82.0 | thinking effort | — | EuroEval |
| Terminal-Bench 1.0 | Agentic | 61.3% | 63.4 | — | 12 Jan 2026 | Vals AI |
| EuroEval Spanish | Multilingual | 60.4% | 77.7 | thinking effort | — | EuroEval |
| EuroEval German | Multilingual | 57.1% | 73.6 | thinking effort | — | EuroEval |
| Terminal-Bench 2.0 | Agentic | 41.6% | 52.3 | — | 4 Jun 2026 | Vals AI |
| Vibe Code Bench v1.1 | Coding | 22.6% | 51.6 | OpenHands | 21 Sept 2026 | Vals AI |
| IOI v1 | Coding | 18.3% | 50.4 | — | 9 Aug 2026 | Vals AI |
11 benchmarks count, from 18 of 19 results. A grey row does not count. Too few models took that benchmark.