# Claude Opus 4.6 vs GPT-5.1

> Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 48.8 on the Noometry Index. GPT-5.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-6-vs-gpt-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 48

## Summary

- They share 48 benchmarks with published results for both. Claude Opus 4.6 scores higher in 8 categories and GPT-5.1 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Opus 4.6 leads 51.0 to 32.5.
- The biggest single-benchmark swing is ARC-AGI-2: 69.2% for Claude Opus 4.6 and 17.6% for GPT-5.1.
- GPT-5.1 is cheaper at $1.25 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
- Claude Opus 4.6 accepts more context: 1M tokens versus 400K.

## Snapshot

| | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.3 | 48.8 |
| Rank | 18 | 47 |
| Context | 1M | 400K |
| Input $/M | $5 | $1.25 |
| Output $/M | $25 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.6: 57.7 (#15)
- GPT-5.1: 46.9 (#59)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| SWE-bench Verified | 78.7% | 68% |
| SWE-bench Verified (bash only) | 75.6% | 66% |
| LMArena WebDev | 1546 | 1395 |
| GSO | 41.2% | 13.7% |
| WeirdML | 78% | 60.8% |
| LMArena Coding | 1535 | 1454 |
| ALE-Bench | 996.5 | 1,192 |
| FrontierCode | 26.6% | — |
| SWE-bench Multilingual | 72% | — |
| SciCode | — | 43.3% |
| LiveBench Coding | — | 72.5% |
| AlgoTune | 1.47 | — |

## Agentic & Tool Use

- Claude Opus 4.6: 51.0 (#4)
- GPT-5.1: 32.5 (#55)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| Terminal-Bench | 79.8% | 47.6% |
| DeepResearch Bench | 55.3% | 42.8% |
| LMArena Search | 1253 | 1199 |
| Vending-Bench 2 | 8,018 | 1,473 |
| APEX-Agents | 46.3% | — |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| GBAEval | 44.1% | — |
| METR Time Horizons | 78.9% | — |

## Reasoning

- Claude Opus 4.6: 57.7 (#21)
- GPT-5.1: 39.9 (#50)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| ARC-AGI-2 | 69.2% | 17.6% |
| SimpleBench | 67.6% | 53.2% |
| ARC-AGI-1 | 94% | 72.8% |
| Chess Puzzles | 17% | 32% |
| EnigmaEval | 7.6% | 11.2% |
| LMArena Hard Prompts | 1527 | 1457 |
| Mystery Game Puzzles | 25% | 19% |
| DTBench | 91.2% | 90.1% |
| LMCA | 55.8% | 43.9% |
| Epoch Capabilities Index | 155.36 | 149.66 |
| ForecastBench | 60 | 58.1 |
| Kagi LLM Benchmark | 83.6% | — |
| NYT Connections (extended) | 92.1% | — |
| CritPt | — | 4.9% |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |
| LiveBench Reasoning | — | 95.8% |
| LiveBench Data Analysis | — | 72.1% |
| LiveBench | — | 78.8% |

## Math

- Claude Opus 4.6: 62.7 (#25)
- GPT-5.1: 50.3 (#45)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 88.6% |
| LMArena Math | 1517 | 1446 |
| FrontierMath (Feb 2025 set) | 40.7% | 31% |
| FrontierMath Tier 4 (v1) | 22.9% | 12.5% |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 78.5% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 46.4% |
| LiveBench Math | — | 94.5% |

## Knowledge

- Claude Opus 4.6: 61.8 (#23)
- GPT-5.1: 50.5 (#65)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 90.5% | 87.6% |
| Humanity's Last Exam | 34.4% | 23.7% |
| SimpleQA Verified | 47% | 48% |
| Vectara Hallucination Rate | 12.2% | 10.9% |
| LMArena Expert | 1546 | 1470 |
| MMLU-Pro | — | 57.9% |
| GPQA (HELM) | — | 44.2% |

## Multimodal

- Claude Opus 4.6: 37.0 (#67)
- GPT-5.1: 44.0 (#17)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1316 | 1250 |
| LMArena Document | 1507 | 1403 |
| VPCT | — | 58.7% |
| Furniture Assembly | 28.3% | — |

## Multilingual

- Claude Opus 4.6: 58.2 (#4)
- GPT-5.1: 54.0 (#51)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1490 | 1431 |
| LMArena Chinese | 1551 | 1495 |
| LMArena French | 1513 | 1451 |
| LMArena German | 1504 | 1439 |
| LMArena Japanese | 1484 | 1453 |
| LMArena Korean | 1465 | 1401 |
| LMArena Russian | 1497 | 1435 |
| LMArena Spanish | 1512 | 1430 |

## Instruction Following

- Claude Opus 4.6: 79.7 (#3)
- GPT-5.1: 84.0 (#1)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| LMArena Instruction Following | 1523 | 1442 |
| LiveBench Instruction Following | — | 93.3% |
| IFEval | — | 93.5% |

## Long Context

- Claude Opus 4.6: 48.1 (#13)
- GPT-5.1: 47.6 (#14)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| CL-bench | 20.7% | 23.7% |
| CL-bench Life | 17% | 17.3% |
| LMArena Longer Query | 1520 | 1448 |

## Writing & Preference

- Claude Opus 4.6: 73.7 (#9)
- GPT-5.1: 64.7 (#53)

| Benchmark | Claude Opus 4.6 | GPT-5.1 |
|---|---|---|
| LMArena Text | 1504 | 1443 |
| LMArena Creative Writing | 1506 | 1427 |
| LMArena Multi-Turn | 1514 | 1449 |
| EQ-Bench Creative Writing | 1809 | — |
| WildBench | — | 86.3% |
| EQ-Bench 4 | 1223 | — |
| LiveBench Language | — | 80.2% |

## FAQ

### Is Claude Opus 4.6 better than GPT-5.1?

Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 48.8 on the Noometry Index. GPT-5.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.6 or GPT-5.1?

GPT-5.1 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

### Is Claude Opus 4.6 or GPT-5.1 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.7 versus 46.9 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 400K.

### How many benchmarks do Claude Opus 4.6 and GPT-5.1 share?

48 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GPT-5.1 has 63.