Inference360
Anthropic

Claude 3.7 Sonnet

Claude 3.7 Sonnet is a model from Anthropic. 12 benchmarks count toward its score, in 5 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.40.3 ±7.2
CoverageShare of the index weight with results.75%
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.N/A
EloLMArena rating and rank.1299 (#235)

The index is a score out of 100. The ± range shows how much it can change.

42,448 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
44.9
CodingCode writing and repair.
42.2
ReasoningLogic problems and puzzles.
N/A
MultimodalTasks with images and text.
43.7
KnowledgeFacts and expert knowledge.
46.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
33.4

Results

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.
MGSMMultilingual92.4%——9 Jan 2026Vals AI
MATH level 5Math88.1%42.0——Epoch AI
MMLU ProKnowledge80.7%47.6—1 Sept 2026Vals AI
MATH 500Math76.8%27.6—9 Jan 2026Vals AI
GPQA diamondKnowledge76.8%49.1——Epoch AI
τ²-bench RetailAgentic72.1%50.6Sierra30 Apr 2026Sierra Research
MMMU ProMultimodal71.5%43.7—1 Sept 2026Vals AI
GPQA DiamondKnowledge67.4%40.5—1 Sept 2026Vals AI
τ²-bench AirlineAgentic64.2%44.9Sierra2 Mar 2026Sierra Research
SWE-bench VerifiedCoding62.4%47.6SWE-agent1 Sept 2026SWE-bench team
SWE-Bench verifiedCoding61.0%46.4——Epoch AI
LiveCodeBenchCoding56.7%35.9—1 Sept 2026Vals AI
SWE-bench VerifiedCoding52.8%39.9mini-SWE-agent26 Feb 2026SWE-bench team
OTIS Mock AIME 2024-2025Math50.0%39.5——Epoch AI
τ²-bench TelecomAgentic49.0%34.0Sierra2 Mar 2026Sierra Research
SWE-bench LiteCoding48.0%44.2SWE-agent11 Sept 2025SWE-bench team
SWE-bench LiteCoding48.0%44.2SWE-agent11 Sept 2025SWE-bench team
SWE-bench (full test split)Coding33.8%—SWE-agent 1.019 Dec 2025SWE-bench team
SWE-bench MultimodalMultimodal30.9%—OpenHands-Versa17 Nov 2025SWE-bench team
SWE-bench MultimodalMultimodal30.9%—OpenHands-Versa17 Nov 2025SWE-bench team
AIMEMath22.3%24.1—16 Apr 2026Vals AI
FrontierMath-2025-02-28-PrivateMath3.3%33.7——Epoch AI

12 benchmarks count, from 18 of 22 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AIEpoch AI, collected directlyCC BY — free to use and redistribute with attributionSierra Research, collected directlyMIT — results are in the licensed repositorySWE-bench team, collected directlyNo licence stated. The repository publishes submission records for reproducibility and transparency and asks that SWE-bench be cited

More from Anthropic

Claude Opus 5.582.8Claude Fable 5.181.4Claude Opus 577.9Claude Fable 577.5Claude Opus 4.871.1