# Claude Opus 4.1 vs GPT-5 Mini

> Claude Opus 4.1 and GPT-5 Mini score almost the same on the Noometry Index (40.8 vs 41.7), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-opus-4-1-vs-gpt-5-mini
- Last updated: 2026-10-10
- Shared benchmarks: 40

## Summary

- They share 40 benchmarks with published results for both. Claude Opus 4.1 scores higher in 6 categories and GPT-5 Mini in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.3 to 22.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 46.7% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- GPT-5 Mini accepts more context: 400K tokens versus 200K.

## Snapshot

| | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 41.7 |
| Rank | 136 | 115 |
| Context | 200K | 400K |
| Input $/M | $15 | $0.25 |
| Output $/M | $75 | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.1: 44.3 (#69)
- GPT-5 Mini: 40.0 (#134)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| SWE-bench Verified | 73.3% | 64.7% |
| WeirdML | 45.9% | 52.7% |
| LMArena Coding | 1479 | 1406 |
| ALE-Bench | 674.77 | 799.77 |
| AlgoTune | 1.34 | 1.38 |
| SWE-bench Verified (bash only) | — | 59.8% |
| LMArena WebDev | 1390 | — |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |

## Agentic & Tool Use

- Claude Opus 4.1: 34.8 (#38)
- GPT-5 Mini: 31.0 (#64)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | 38% | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | -31.18 |

## Reasoning

- Claude Opus 4.1: 31.6 (#70)
- GPT-5 Mini: 24.1 (#153)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| Chess Puzzles | 7% | 30% |
| EnigmaEval | 7.2% | 8.2% |
| LMArena Hard Prompts | 1443 | 1380 |
| Mystery Game Puzzles | 21% | 10% |
| DTBench | 80% | 80.5% |
| LMCA | 37.1% | 34.2% |
| Epoch Capabilities Index | 144.11 | 145.51 |
| ForecastBench | 62 | 61 |
| ARC-AGI-2 | — | 4.4% |
| SimpleBench | 60% | — |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| EBR-Bench | 7.9% | — |

## Math

- Claude Opus 4.1: 22.0 (#267)
- GPT-5 Mini: 46.3 (#59)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 46.7% |
| FrontierMath Tier 4 | 2.4% | 12.2% |
| OTIS Mock AIME 2024-2025 | 68.9% | 86.7% |
| LMArena Math | 1430 | 1377 |
| FrontierMath (Feb 2025 set) | 7.2% | 27.2% |
| FrontierMath Tier 4 (v1) | 4.2% | 6.3% |
| ProofBench | — | 9% |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |

## Knowledge

- Claude Opus 4.1: 41.9 (#93)
- GPT-5 Mini: 45.5 (#80)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 77.3% | 75% |
| Humanity's Last Exam | 11.5% | 19.4% |
| Confabulations | 17.1% | 13.3% |
| Vectara Hallucination Rate | 11.8% | 12.9% |
| LMArena Expert | 1439 | 1377 |
| SimpleQA Verified | — | 21.6% |
| MMLU-Pro | — | 83.5% |
| GPQA (HELM) | — | 75.6% |

## Multimodal

- Claude Opus 4.1: 26.2 (#114)
- GPT-5 Mini: 35.0 (#80)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| VPCT | 35% | 40.2% |
| LMArena Vision | — | 1202 |

## Multilingual

- Claude Opus 4.1: 52.1 (#90)
- GPT-5 Mini: 49.1 (#131)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1405 | 1363 |
| LMArena Chinese | 1427 | 1387 |
| LMArena French | 1432 | 1385 |
| LMArena German | 1412 | 1366 |
| LMArena Japanese | 1378 | 1342 |
| LMArena Korean | 1381 | 1306 |
| LMArena Russian | 1421 | 1362 |
| LMArena Spanish | 1448 | 1355 |

## Instruction Following

- Claude Opus 4.1: 75.8 (#53)
- GPT-5 Mini: 76.4 (#43)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1436 | 1357 |
| IFEval | — | 92.7% |

## Long Context

- Claude Opus 4.1: 44.5 (#60)
- GPT-5 Mini: 41.9 (#127)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1455 | 1355 |
| Fiction.LiveBench | — | 69.4% |

## Writing & Preference

- Claude Opus 4.1: 62.6 (#70)
- GPT-5 Mini: 55.4 (#143)

| Benchmark | Claude Opus 4.1 | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1419 | 1373 |
| LMArena Creative Writing | 1412 | 1325 |
| Short-Story Creative Writing | 84.7% | 83.1% |
| LMArena Multi-Turn | 1444 | 1363 |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |

## FAQ

### Is Claude Opus 4.1 better than GPT-5 Mini?

Claude Opus 4.1 and GPT-5 Mini score almost the same on the Noometry Index (40.8 vs 41.7), so choose on price, context window or the category you care about most.

### Which is cheaper, Claude Opus 4.1 or GPT-5 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Claude Opus 4.1 lists at $15 and $75.

### Is Claude Opus 4.1 or GPT-5 Mini better for coding?

Claude Opus 4.1 scores higher on coding benchmarks: 44.3 versus 40.0 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Mini does, with 400K tokens against 200K.

### How many benchmarks do Claude Opus 4.1 and GPT-5 Mini share?

40 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-5 Mini has 60.