# Claude Opus 5 vs GPT-4.1 mini

> Claude Opus 5 is the stronger model overall, scoring 67.7 to 33.5 on the Noometry Index. GPT-4.1 mini costs 14× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-5-vs-gpt-4-1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Claude Opus 5 scores higher in 10 categories and GPT-4.1 mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.1 to 10.9.
- The biggest single-benchmark swing is ARC-AGI-1: 97.5% for Claude Opus 5 and 3.5% for GPT-4.1 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 67.7 | 33.5 |
| Rank | 4 | 232 |
| Context | 1M | 1.05M |
| Input $/M | $5 | $0.40 |
| Output $/M | $25 | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 5: 67.0 (#5)
- GPT-4.1 mini: 30.4 (#286)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| SciCode | 56.4% | 40.4% |
| WeirdML | 91.8% | 37.6% |
| LMArena Coding | 1533 | 1367 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1694 | — |
| FrontierSWE | 52% | — |
| BigCodeBench Instruct | — | 48.9% |
| CadEval | — | 16% |
| ALE-Bench | 2,165 | — |

## Agentic & Tool Use

- Claude Opus 5: 55.5 (#1)
- GPT-4.1 mini: 33.0 (#52)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| APEX-Agents | 65.8% | — |
| Berkeley Function Calling Leaderboard | — | 50.5% |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |

## Reasoning

- Claude Opus 5: 77.1 (#3)
- GPT-4.1 mini: 10.9 (#335)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| ARC-AGI-2 | 90.4% | 0% |
| ARC-AGI-1 | 97.5% | 3.5% |
| CritPt | 29.1% | 0% |
| Chess Puzzles | 42% | 7% |
| LMArena Hard Prompts | 1525 | 1349 |
| Mystery Game Puzzles | 59% | 7% |
| DTBench | 97.9% | 68.8% |
| LMCA | 64.5% | 21.1% |
| Epoch Capabilities Index | 162.67 | 135.01 |
| SimpleBench | 80.6% | — |
| Kagi LLM Benchmark | — | 48.6% |
| NYT Connections (extended) | 94.3% | — |
| EBR-Bench | 45.7% | — |
| Bench to the Future 3 | 0.12 | — |

## Math

- Claude Opus 5: 86.1 (#6)
- GPT-4.1 mini: 23.1 (#264)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 6.7% |
| OTIS Mock AIME 2024-2025 | 98.9% | 44.7% |
| LMArena Math | 1533 | 1343 |
| FrontierMath Tier 4 | 73.2% | — |
| ProofBench | 99% | — |
| Omni-MATH | — | 49.1% |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |

## Knowledge

- Claude Opus 5: 66.8 (#8)
- GPT-4.1 mini: 34.7 (#183)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 93.9% | 65.8% |
| SimpleQA Verified | 59.9% | 12.7% |
| LMArena Expert | 1558 | 1338 |
| MMLU-Pro | — | 78.3% |
| GPQA (HELM) | — | 61.4% |

## Multimodal

- Claude Opus 5: 51.1 (#6)
- GPT-4.1 mini: 35.2 (#77)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | 1321 | 1181 |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |

## Multilingual

- Claude Opus 5: 58.8 (#3)
- GPT-4.1 mini: 45.9 (#161)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1500 | 1318 |
| LMArena Chinese | 1575 | 1329 |
| LMArena French | 1522 | 1357 |
| LMArena German | 1522 | 1349 |
| LMArena Japanese | 1510 | 1291 |
| LMArena Korean | 1526 | 1298 |
| LMArena Russian | 1507 | 1324 |
| LMArena Spanish | 1519 | 1319 |

## Instruction Following

- Claude Opus 5: 79.3 (#5)
- GPT-4.1 mini: 73.9 (#113)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| LMArena Instruction Following | 1516 | 1332 |
| IFEval | — | 90.4% |

## Long Context

- Claude Opus 5: 46.5 (#20)
- GPT-4.1 mini: 31.8 (#270)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1516 | 1344 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- Claude Opus 5: 79.3 (#2)
- GPT-4.1 mini: 48.8 (#193)

| Benchmark | Claude Opus 5 | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1506 | 1341 |
| LMArena Creative Writing | 1491 | 1300 |
| EQ-Bench Creative Writing | 2133 | 1147 |
| LMArena Multi-Turn | 1496 | 1354 |
| WildBench | — | 83.8% |
| EQ-Bench 4 | 1385 | — |

## FAQ

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

Claude Opus 5 is the stronger model overall, scoring 67.7 to 33.5 on the Noometry Index. GPT-4.1 mini costs 14× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

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

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Claude Opus 5 lists at $5 and $25.

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

Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 30.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 1M.

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

33 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and GPT-4.1 mini has 47.