Models / Claude Opus 4.7

Anthropic

Claude Opus 4.7

45 published results from 6 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider: Anthropic
Sources: 6
Our benchmarks: 0
Price: Not yet published

Reported by others

Reported by Arena (formerly LMArena)

1,494

Overall · rank 1 of 44

Unit: Arena rating, higher is better
Range: 1,488 to 1,501
Sample: 22192 votes
Configuration: Claude Opus 4.7
Measured: 13 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,493

Overall · rank 1 of 44

Unit: Arena rating, higher is better
Range: 1,486 to 1,500
Sample: 21957 votes
Configuration: Claude Opus 4.7 (high)
Measured: 13 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,212

Overall · rank 5 of 34

Unit: Arena rating, higher is better
Range: 1,207 to 1,218
Sample: 91394 votes
Configuration: Claude Opus 4.7
Measured: 24 Aug 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,475

Overall · rank 9 of 177

Unit: Arena rating, higher is better
Range: 1,472 to 1,479
Sample: 64953 votes
Configuration: Claude Opus 4.7
Measured: 25 Sep 2026
Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Reported by Arena (formerly LMArena)

1,477

Overall · rank 7 of 177

Unit: Arena rating, higher is better
Range: 1,474 to 1,480
Sample: 63912 votes
Configuration: Claude Opus 4.7 (high)
Measured: 25 Sep 2026
Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Reported by Arena (formerly LMArena)

1,495

Business, management and finance · rank 1 of 402

Unit: Arena rating, higher is better
Range: 1,489 to 1,502
Sample: 13082 votes
Configuration: Claude Opus 4.7
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,508

Business, management and finance · rank 1 of 402

Unit: Arena rating, higher is better
Range: 1,501 to 1,514
Sample: 12876 votes
Configuration: Claude Opus 4.7 (high)
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,484

Creative writing · rank 4 of 407

Unit: Arena rating, higher is better
Range: 1,477 to 1,491
Sample: 11591 votes
Configuration: Claude Opus 4.7
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,488

Creative writing · rank 1 of 407

Unit: Arena rating, higher is better
Range: 1,481 to 1,496
Sample: 11381 votes
Configuration: Claude Opus 4.7 (high)
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,535

Expert prompts · rank 1 of 359

Unit: Arena rating, higher is better
Range: 1,527 to 1,543
Sample: 6985 votes
Configuration: Claude Opus 4.7
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,534

Expert prompts · rank 1 of 359

Unit: Arena rating, higher is better
Range: 1,526 to 1,542
Sample: 6825 votes
Configuration: Claude Opus 4.7 (high)
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,494

Instruction following · rank 3 of 409

Unit: Arena rating, higher is better
Range: 1,488 to 1,499
Sample: 23030 votes
Configuration: Claude Opus 4.7
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,503

Instruction following · rank 2 of 409

Unit: Arena rating, higher is better
Range: 1,497 to 1,508
Sample: 22448 votes
Configuration: Claude Opus 4.7 (high)
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,495

Overall · rank 3 of 409

Unit: Arena rating, higher is better
Range: 1,491 to 1,498
Sample: 65051 votes
Configuration: Claude Opus 4.7
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,502

Overall · rank 1 of 409

Unit: Arena rating, higher is better
Range: 1,498 to 1,506
Sample: 64007 votes
Configuration: Claude Opus 4.7 (high)
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,485

Writing, literature and language · rank 4 of 408

Unit: Arena rating, higher is better
Range: 1,478 to 1,491
Sample: 16514 votes
Configuration: Claude Opus 4.7
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Arena (formerly LMArena)

1,496

Writing, literature and language · rank 1 of 408

Unit: Arena rating, higher is better
Range: 1,490 to 1,502
Sample: 16137 votes
Configuration: Claude Opus 4.7 (high)
Measured: 25 Sep 2026
Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Reported by Microsoft STATE-Bench

33.9%

Consistency (pass^5) · rank 2 of 5

Unit: % of tasks, higher is better
Configuration: claude-opus-4.7
Measured: 29 May 2026
Not shown: Not the model alone: it runs inside STATE-Bench's agent loop against simulated users, and versions of the benchmark are not comparable.

Reported by Microsoft STATE-Bench

51.0%

Customer support task success (pass@1) · rank 2 of 5

Unit: % of tasks, higher is better
Configuration: claude-opus-4.7
Measured: 29 May 2026
Not shown: Not the model alone: it runs inside STATE-Bench's agent loop against simulated users, and versions of the benchmark are not comparable.

Reported by Microsoft STATE-Bench

54.0%

Shopping assistant task success (pass@1) · rank 1 of 5

Unit: % of tasks, higher is better
Configuration: claude-opus-4.7
Measured: 29 May 2026
Not shown: Not the model alone: it runs inside STATE-Bench's agent loop against simulated users, and versions of the benchmark are not comparable.

Reported by Microsoft STATE-Bench

53.4%

Task success (pass@1) · rank 2 of 5

Unit: % of tasks, higher is better
Configuration: claude-opus-4.7
Measured: 29 May 2026
Not shown: Not the model alone: it runs inside STATE-Bench's agent loop against simulated users, and versions of the benchmark are not comparable.

Reported by Microsoft STATE-Bench

55.0%

Travel task success (pass@1) · rank 2 of 5

Unit: % of tasks, higher is better
Configuration: claude-opus-4.7
Measured: 29 May 2026
Not shown: Not the model alone: it runs inside STATE-Bench's agent loop against simulated users, and versions of the benchmark are not comparable.

Reported by Microsoft STATE-Bench

3.46

User experience · rank 2 of 5

Unit: score from 1 to 5, higher is better
Configuration: claude-opus-4.7
Measured: 29 May 2026
Not shown: Not real customer satisfaction: the ratings come from a model-based judge.

Reported by OpenHands Index

69.7%

Average · rank 3 of 34

Unit: % resolved, higher is better
Configuration: claude-opus-4.7
Measured: 30 Jun 2026
Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Reported by OpenHands Index

48.5%

Front end (SWE-Bench Multimodal) · rank 3 of 34

Unit: % resolved, higher is better
Configuration: claude-opus-4.7
Measured: 30 Jun 2026
Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Reported by OpenHands Index

56.2%

Greenfield (Commit0) · rank 3 of 34

Unit: % resolved, higher is better
Configuration: claude-opus-4.7
Measured: 30 Jun 2026
Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Reported by OpenHands Index

81.2%

Information gathering (GAIA) · rank 5 of 34

Unit: % resolved, higher is better
Configuration: claude-opus-4.7
Measured: 30 Jun 2026
Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Reported by OpenHands Index

81.6%

Issue resolution (SWE-Bench) · rank 3 of 34

Unit: % resolved, higher is better
Configuration: claude-opus-4.7
Measured: 30 Jun 2026
Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Reported by OpenHands Index

80.8%

Testing (SWT-Bench) · rank 5 of 34

Unit: % resolved, higher is better
Configuration: claude-opus-4.7
Measured: 30 Jun 2026
Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Reported by tau2-bench

24.7%

Consistency (pass^4) · rank 7 of 21

Unit: % of tasks, higher is better
Configuration: claude-opus-4.7
Measured: 23 Jul 2026
Not shown: Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.

Reported by tau2-bench

40.2%

Task success (pass^1) · rank 7 of 21

Unit: % of tasks, higher is better
Configuration: claude-opus-4.7
Measured: 23 Jul 2026
Not shown: Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.

Reported by UGI Leaderboard

2.0%

Requested-length error · rank 7 of 370

Unit: % off the requested word count, lower is better
Configuration: Claude Opus 4.7 (high)
Measured: 16 Apr 2026
Not shown: Not other format limits such as character counts or bullet counts.

Reported by UGI Leaderboard

1.0%

Requested-length error · rank 3 of 370

Unit: % off the requested word count, lower is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not other format limits such as character counts or bullet counts.

Reported by UGI Leaderboard

3.0%

Requested-length error · rank 18 of 370

Unit: % off the requested word count, lower is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not other format limits such as character counts or bullet counts.

Reported by UGI Leaderboard

2.0%

Requested-length error · rank 7 of 370

Unit: % off the requested word count, lower is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not other format limits such as character counts or bullet counts.

Reported by UGI Leaderboard

0.41

Style adherence · rank 8 of 370

Unit: score from 0 to 1, higher is better
Configuration: Claude Opus 4.7 (high)
Measured: 16 Apr 2026
Not shown: Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.

Reported by UGI Leaderboard

0.39

Style adherence · rank 43 of 370

Unit: score from 0 to 1, higher is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.

Reported by UGI Leaderboard

0.40

Style adherence · rank 23 of 370

Unit: score from 0 to 1, higher is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.

Reported by UGI Leaderboard

0.40

Style adherence · rank 19 of 370

Unit: score from 0 to 1, higher is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.

Reported by UGI Leaderboard

56.9

Writing score · rank 119 of 370

Unit: score out of 100, higher is better
Configuration: Claude Opus 4.7 (high)
Measured: 16 Apr 2026
Not shown: Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.

Reported by UGI Leaderboard

56.9

Writing score · rank 118 of 370

Unit: score out of 100, higher is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.

Reported by UGI Leaderboard

61.4

Writing score · rank 91 of 370

Unit: score out of 100, higher is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.

Reported by UGI Leaderboard

56.6

Writing score · rank 122 of 370

Unit: score out of 100, higher is better
Configuration: claude-opus-4.7
Measured: 16 Apr 2026
Not shown: Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.

Reported by Vectara Hallucination Leaderboard

98.0%

Answer rate · rank 82 of 108

Unit: % of documents, higher is better
Configuration: Claude Opus 4.7
Measured: 22 Sep 2026
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Reported by Vectara Hallucination Leaderboard

12.0%

Hallucination rate · rank 78 of 108

Unit: % of summaries, lower is better
Configuration: Claude Opus 4.7
Measured: 22 Sep 2026
Not shown: Not errors in open questions or other tasks: only summarisation, judged by Vectara's own model (HHEM-2.3), not by people, on news-style documents rather than your data.

Claude Opus 4.7

Reported by others

Compare Claude Opus 4.7 with