Anthropic
availableShows if the model has enough results for an index.Claude 3.5 Sonnet
Claude 3.5 Sonnet is a non-reasoning model from Anthropic. 12 benchmarks count toward its score, in 4 categories.
IndexOverall score out of 100.31.8 ±9.2
CoverageShare of the index weight with results.55%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.$3
Output / 1MUS dollars per 1M output tokens.$15
ContextMaximum tokens in one request.200K
EloLMArena rating and rank.1281 (#257)
The index is a score out of 100. The ± range shows how much it can change.
82,419 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
12 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 | 92.6% | — | — | 9 Jan 2026 | Vals AI |
| MMLU Pro | Knowledge | 78.4% | 44.0 | — | 1 Sept 2026 | Vals AI |
| MATH 500 | Math | 72.4% | 22.7 | — | 9 Jan 2026 | Vals AI |
| MMMU Pro | Multimodal | 68.8% | 39.3 | — | 1 Sept 2026 | Vals AI |
| Graduate-Level Google-Proof Q&A | Knowledge | 59.4% | 33.1 | — | — | David Rein et al. |
| GPQA Diamond | Knowledge | 59.3% | 33.0 | — | 1 Sept 2026 | Vals AI |
| GPQA diamond | Knowledge | 54.0% | 28.1 | — | — | Epoch AI |
| SWE-bench Verified | Coding | 53.0% | 40.0 | Engine Labs | 1 Sept 2026 | SWE-bench team |
| MATH level 5 | Math | 51.7% | 24.1 | — | — | Epoch AI |
| LiveCodeBench | Coding | 49.6% | 29.5 | — | 1 Sept 2026 | Vals AI |
| Software Engineering Benchmark Verified | Coding | 49.0% | 36.8 | — | — | Carlos E. Jimenez et al. |
| SWE-bench Lite | Coding | 40.8% | 38.1 | Agentless-1.5 | 11 Sept 2025 | SWE-bench team |
| SWE-bench Verified | Coding | 33.6% | 24.5 | SWE-agent | 26 Feb 2026 | SWE-bench team |
| SWE-bench Lite | Coding | 30.0% | 28.8 | Kortix AI | 11 Sept 2025 | SWE-bench team |
| SWE-bench (full test split) | Coding | 21.5% | — | SWE-agent | 19 Dec 2025 | SWE-bench team |
| AIME | Math | 10.0% | 18.4 | — | 16 Apr 2026 | Vals AI |
| SWE-bench Multimodal | Multimodal | 8.8% | — | Agentless | 17 Nov 2025 | SWE-bench team |
| SWE-bench Multimodal | Multimodal | 8.8% | — | SWE-agent Multimodal | 17 Nov 2025 | SWE-bench team |
| OTIS Mock AIME 2024-2025 | Math | 6.5% | 15.3 | — | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 1.0% | 31.6 | — | — | Epoch AI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 0.0% | 43.4 | — | — | Epoch AI |
12 benchmarks count, from 17 of 21 results. A grey row does not count. Too few models took that benchmark.