BlogLLM Benchmark Scores as Published, Side by Side
Claude Opus 4.7: Benchmark Scores as Published
Every result the catalog holds for Claude Opus 4.7: 59 tests in 15 areas, from 9 pages. 19 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 2026-04-16Context window 1MMax output 128KInput Text, imageOutput TextWeights ClosedData version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| APEX-Agents | 37.2% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| GDPval-AA (Elo) | 1753 | Anthropic, Claude Opus 4.8checked 2026-10-15; printed on 1 more page | - |
| Vals Finance Agent v2 | 51.5% | Anthropic, Claude Opus 4.8checked 2026-10-15; printed on 1 more page | - |
| OfficeQA Pro | 43.6% | MiniMax, MiniMax M3checked 2026-10-15; printed on 1 more page | Harness: Claude Code |
| Vals Finance Agent v1.1 | 64.4% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page | - |
| GDPval (wins or ties) | 80.3% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | - |
| GDPval rubrics (pointwise rubric score) | 79.8% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| SpreadsheetBench v1 | 88.49% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| YC-Bench (final assets, USD) | $2190000 | MiniMax, MiniMax M3checked 2026-10-15 | - |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 87.6% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page | - |
| SWE-Bench Pro | 64.3% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 5 more pages | - |
| Terminal-Bench 2.1 | 66.1% | Anthropic, Claude Opus 4.8checked 2026-10-15; printed on 3 more pages | Harness: Terminus-2 |
| Terminal-Bench 2.0 | 69.4% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page | Harness: Terminus-2, thinking disabled |
| NL2Repo-Bench | 56.28 | MiniMax, MiniMax M3checked 2026-10-15 | - |
| SWE-Marathon | 16% | xAI, Grok 4.5checked 2026-10-15 | Effort: max |
| SWE-Atlas-QnA (setting not stated) | 45.16% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| SWE-Atlas-Test Writing | 38.21% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| DeepSWE v1.0 | 40.12% | xAI, Grok 4.5checked 2026-10-15 | Effort: max; Harness: each provider's own harness (Artificial Analysis run) |
| SWE-fficiency | 42.2% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| VIBE-V2 (MiniMax internal) | 55.87% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
ML Engineering
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| PaperBench | 58.5 | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| KernelBench Hard (TFLOPs relative to hardware peak) | 30.7% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| PostTrainBench (version not stated) | 42.4% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 94.2% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page | - |
| FrontierMath Tier 1-3 | 43.8% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | - |
| FrontierMath Tier 4 | 22.9% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | - |
| USAMO 2026 (share of the maximum score) | 52.8% | MiniMax, MiniMax M3checked 2026-10-15 | - |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MRCR v2 8-needle 128K | 59.3% | Google, Gemini 3.5 Flash model cardchecked 2026-10-15 | Context: 128k (average) |
| GraphWalks BFS 1M (F1) | 41.2% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Context: 1M |
| GraphWalks BFS 256k (F1) | 76.9% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Context: 256k |
| MRCR v2 8-needle 128K-256K | 59.2% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Context: 128K-256K |
| LOCA-Bench (256k environment description) | 57% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| MRCR v2 8-needle 512K-1M | 32.2% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Context: 512K-1M |
| GraphWalks parents 1M (F1) | 72% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Context: 1M |
| GraphWalks parents 256k (F1) | 93.6% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | Context: 256k |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld-Verified | 78% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 4 more pages | - |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CharXiv Reasoning (no tools) | 82.1% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page | Tools: none |
| MMMU-Pro | 75.2% | Google, Gemini 3.5 Flash model cardchecked 2026-10-15; printed on 1 more page | Tools: none |
| CharXiv Reasoning (with tools) | 91% | Anthropic, Claude Opus 4.7checked 2026-10-15 | Tools: enabled; exact tools in source |
| OmniDocBench 1.5 | 89.3% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Video-MMMU | 83% | MiniMax, MiniMax M3checked 2026-10-15 | - |
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CyberGym | 73.1% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 1 more page | - |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 46.9% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 3 more pages | Tools: none |
| Humanity's Last Exam (with tools) | 54.7% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 2 more pages | Tools: enabled; exact tools in source |
| ARC-AGI-2 | 75.8% | Google, Gemini 3.5 Flash model cardchecked 2026-10-15; printed on 1 more page | - |
| ARC-AGI-1 | 93.5% | OpenAI, Introducing GPT-5.5checked 2026-10-15 | - |
| CL-bench | 22.92% | MiniMax, MiniMax M3checked 2026-10-15 | - |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveSQLBench (Base-Full v1) | 41% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
| SVG-Bench (MiniMax internal) | 62.3% | MiniMax, MiniMax M3checked 2026-10-15 | Harness: Claude Code |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MCP Atlas | 77.3% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 2 more pages | - |
| MCP Atlas (public set) | 77% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Claw-Eval pass^3 | 71.6% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| BankerToolBench | 81.34% | MiniMax, MiniMax M3checked 2026-10-15 | - |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 79.3% | Anthropic, Claude Opus 4.7checked 2026-10-15; printed on 2 more pages | - |
| DRACO | 77.7% | MiniMax, MiniMax M3checked 2026-10-15 | - |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMMLU | 91.5% | Anthropic, Claude Opus 4.7checked 2026-10-15 | - |
Safety and Alignment
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Self-preference bias, Claude-identity system prompt (0-9 scale)lower is better | 0.4 | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Self-preference bias, no system prompt (0-9 scale)lower is better | 0.27 | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
Engineering and Design
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Blueprint-Bench 2 (normalized score) | 24.5% | Google, Gemini 3.5 Flash model cardchecked 2026-10-15 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $5 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Cached input | $0.5 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Cache write | $6.25 | Anthropic, Anthropic API pricingchecked 2026-10-15 | Cache: 5 minute cache |
| Cache write, 1 hour | $10 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Output | $25 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Input, batch | $2.5 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Output, batch | $12.5 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Cost per taskVals AI, USD, lower is better | $21.41 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27 | Harness: OpenHands |
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 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 3.7 Sonnet
- 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.