# Claude Opus 4.6 vs GPT-5 Mini

> Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 41.7 on the Noometry Index. GPT-5 Mini costs 15× 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-mini
- Last updated: 2026-10-10
- Shared benchmarks: 47

## Summary

- They share 47 benchmarks with published results for both. Claude Opus 4.6 scores higher in 10 categories and GPT-5 Mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.6 leads 57.7 to 24.1.
- The biggest single-benchmark swing is ARC-AGI-2: 69.2% for Claude Opus 4.6 and 4.4% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 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 Mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.3 | 41.7 |
| Rank | 18 | 115 |
| Context | 1M | 400K |
| Input $/M | $5 | $0.25 |
| Output $/M | $25 | $2 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.6: 57.7 (#15)
- GPT-5 Mini: 40.0 (#134)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| SWE-bench Verified | 78.7% | 64.7% |
| SWE-bench Verified (bash only) | 75.6% | 59.8% |
| SWE-bench Multilingual | 72% | 39.7% |
| WeirdML | 78% | 52.7% |
| LMArena Coding | 1535 | 1406 |
| ALE-Bench | 996.5 | 799.77 |
| AlgoTune | 1.47 | 1.38 |
| FrontierCode | 26.6% | — |
| LMArena WebDev | 1546 | — |
| SciCode | — | 39.2% |
| GSO | 41.2% | — |

## Agentic & Tool Use

- Claude Opus 4.6: 51.0 (#4)
- GPT-5 Mini: 31.0 (#64)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | 79.8% | 34.8% |
| Vending-Bench 2 | 8,018 | -31.18 |
| APEX-Agents | 46.3% | — |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| GBAEval | 44.1% | — |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |

## Reasoning

- Claude Opus 4.6: 57.7 (#21)
- GPT-5 Mini: 24.1 (#153)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 69.2% | 4.4% |
| Kagi LLM Benchmark | 83.6% | 70.3% |
| ARC-AGI-1 | 94% | 54.3% |
| Chess Puzzles | 17% | 30% |
| EnigmaEval | 7.6% | 8.2% |
| LMArena Hard Prompts | 1527 | 1380 |
| Mystery Game Puzzles | 25% | 10% |
| DTBench | 91.2% | 80.5% |
| LMCA | 55.8% | 34.2% |
| Epoch Capabilities Index | 155.36 | 145.51 |
| ForecastBench | 60 | 61 |
| SimpleBench | 67.6% | — |
| NYT Connections (extended) | 92.1% | — |
| CritPt | — | 0% |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |

## Math

- Claude Opus 4.6: 62.7 (#25)
- GPT-5 Mini: 46.3 (#59)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 46.7% |
| FrontierMath Tier 4 | 26.8% | 12.2% |
| OTIS Mock AIME 2024-2025 | 94.4% | 86.7% |
| ProofBench | 50% | 9% |
| LMArena Math | 1517 | 1377 |
| FrontierMath (Feb 2025 set) | 40.7% | 27.2% |
| FrontierMath Tier 4 (v1) | 22.9% | 6.3% |
| MathArena Final-Answer Competitions | 78.5% | — |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |

## Knowledge

- Claude Opus 4.6: 61.8 (#23)
- GPT-5 Mini: 45.5 (#80)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 90.5% | 75% |
| Humanity's Last Exam | 34.4% | 19.4% |
| SimpleQA Verified | 47% | 21.6% |
| Vectara Hallucination Rate | 12.2% | 12.9% |
| LMArena Expert | 1546 | 1377 |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| GPQA (HELM) | — | 75.6% |

## Multimodal

- Claude Opus 4.6: 37.0 (#67)
- GPT-5 Mini: 35.0 (#80)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1316 | 1202 |
| VPCT | — | 40.2% |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |

## Multilingual

- Claude Opus 4.6: 58.2 (#4)
- GPT-5 Mini: 49.1 (#131)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1490 | 1363 |
| LMArena Chinese | 1551 | 1387 |
| LMArena French | 1513 | 1385 |
| LMArena German | 1504 | 1366 |
| LMArena Japanese | 1484 | 1342 |
| LMArena Korean | 1465 | 1306 |
| LMArena Russian | 1497 | 1362 |
| LMArena Spanish | 1512 | 1355 |

## Instruction Following

- Claude Opus 4.6: 79.7 (#3)
- GPT-5 Mini: 76.4 (#43)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1523 | 1357 |
| IFEval | — | 92.7% |

## Long Context

- Claude Opus 4.6: 48.1 (#13)
- GPT-5 Mini: 41.9 (#127)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1520 | 1355 |
| Fiction.LiveBench | — | 69.4% |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |

## Writing & Preference

- Claude Opus 4.6: 73.7 (#9)
- GPT-5 Mini: 55.4 (#143)

| Benchmark | Claude Opus 4.6 | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1504 | 1373 |
| LMArena Creative Writing | 1506 | 1325 |
| EQ-Bench Creative Writing | 1809 | 1313 |
| LMArena Multi-Turn | 1514 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| WildBench | — | 85.5% |
| EQ-Bench 4 | 1223 | — |

## FAQ

### Is Claude Opus 4.6 better than GPT-5 Mini?

Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 41.7 on the Noometry Index. GPT-5 Mini costs 15× 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 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

### Is Claude Opus 4.6 or GPT-5 Mini better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.7 versus 40.0 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 Mini share?

47 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GPT-5 Mini has 60.