BlogLLM Benchmark Scores as Published, Side by Side
Claude 3.7 Sonnet: Benchmark Scores as Published
Every result the catalog holds for Claude 3.7 Sonnet: 23 tests in 11 areas, from 5 pages. 12 printed by Anthropic itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer AnthropicReleased 2025-02-24Data version 2026103001, as of 2026-10-30
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 70.3% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page | Effort: none; Harness: custom scaffold with internal scoring on a reduced subset of problems |
| 62.3% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: none | |
| Terminal-Bench (version not stated) | 35.2% | Anthropic, Claude Opus 4 and Claude Sonnet 4checked 2026-10-15 | - |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 78.2% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 3 more pages | Effort: extended thinking, 64K |
| 68% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: none | |
| 84.8% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: extended thinking, 64K; Attempt budget: parallel test-time compute: multiple samples, the best selected by an internal scoring model | |
| AIME 2025 | 54.8% | Anthropic, Claude Opus 4 and Claude Sonnet 4checked 2026-10-15 | - |
| AIME 2024 | 80% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page | Effort: extended thinking, 64K; Attempt budget: parallel test-time compute: multiple samples, the best selected by an internal scoring model |
| 61.3% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: extended thinking, 64K | |
| 23.3% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: none | |
| MATH-500 | 96.2% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 2 more pages | Effort: extended thinking, 64K |
| 82.2% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: none |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| RULER at 128K | 93.8% | Mistral AI, Medium is the new largechecked 2026-10-15 | Context: 128000 |
| RULER at 32K | 95.7% | Mistral AI, Medium is the new largechecked 2026-10-15 | Context: 32000 |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld-Verified | 28% | Anthropic, Claude Sonnet 4.6checked 2026-10-15 | - |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMMU (validation) | 75% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 2 more pages | Effort: extended thinking, 64K |
| 71.8% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: none | |
| AI2D (test) | 78.8% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| ChartQA | 76.3% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| DocVQA (ANLS) | 84.3 | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMLU-Pro | 80.7% | DeepSeek, DeepSeek-V3-0324 model cardchecked 2026-10-15; printed on 1 more page | - |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 36% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| LiveCodeBench (version not stated) | 42.2% | DeepSeek, DeepSeek-V3-0324 model cardchecked 2026-10-15 | - |
| MultiPL-E | 83.4% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
| HumanEval | 92.1% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| τ-bench Airline | 58.4% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page | Effort: none |
| τ-bench Retail | 81.2% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page | Effort: none |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFEval | 93.2% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page | Effort: extended thinking, 64K |
| 90.8% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: none |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMMLU | 86.1% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15; printed on 1 more page | Effort: extended thinking, 64K |
| 83.2% | Anthropic, Claude 3.7 Sonnetchecked 2026-10-15 | Effort: none |
Preference and Composite Rankings
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Arena-Hard win rate (GPT-4-1106 judge) | 93.2% | Mistral AI, Medium is the new largechecked 2026-10-15 | - |
More from Anthropic
- Claude Haiku 5.5
- Claude Sonnet 5.5
- Claude Opus 5.5
- Claude Fable 5.1
- Claude Mythos 5.1
- Claude Opus 5
- Claude Sonnet 5
- Claude Fable 5
- Claude Mythos 5
- Claude Opus 4.8
- Claude Opus 4.7
- Claude Mythos Preview
- Claude Sonnet 4.6
- Claude Opus 4.6
- Claude Opus 4.5
- Claude Haiku 4.5
- Claude Sonnet 4.5
- Claude Opus 4.1
- Claude Opus 4
- Claude Sonnet 4
- Claude 3.5 Sonnet
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.