# Claude Opus 4.6 vs GPT-4o mini

> Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 25.5 on the Noometry Index. GPT-4o mini costs 38× 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-4o-mini
- Last updated: 2026-10-12
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. Claude Opus 4.6 scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.6 leads 63.0 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for Claude Opus 4.6 and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
- Claude Opus 4.6 accepts more context: 1M tokens versus 128K.

## Snapshot

| | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.2 | 25.5 |
| Rank | 20 | 343 |
| Context | 1M | 128K |
| Input $/M | $5 | $0.15 |
| Output $/M | $25 | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.6: 57.2 (#20)
- GPT-4o mini: 22.0 (#335)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| WeirdML | 78% | 11.8% |
| LMArena Coding | 1536 | 1290 |
| SWE-bench Verified | 78.7% | — |
| FrontierCode | 26.6% | — |
| SWE-bench Verified (bash only) | 75.6% | — |
| Aider Polyglot | — | 3.6% |
| LMArena WebDev | 1547 | — |
| SWE-bench Multilingual | 72% | — |
| GSO | 41.2% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 996.5 | — |
| AlgoTune | 1.47 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- Claude Opus 4.6: 51.1 (#4)
- GPT-4o mini: 27.5 (#101)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| Terminal-Bench | 79.8% | — |
| APEX-Agents | 46.3% | — |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| BALROG | — | 17.4% |
| GBAEval | 44.1% | — |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |
| Vending-Bench 2 | 8,018 | — |

## Reasoning

- Claude Opus 4.6: 57.8 (#23)
- GPT-4o mini: 8.7 (#347)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 69.2% | 0% |
| SimpleBench | 67.6% | 10.7% |
| Kagi LLM Benchmark | 83.6% | 28.8% |
| Chess Puzzles | 17% | 0% |
| LMArena Hard Prompts | 1527 | 1267 |
| Mystery Game Puzzles | 25% | 12% |
| DTBench | 91.2% | 54.4% |
| LMCA | 55.8% | 10.4% |
| Epoch Capabilities Index | 155.24 | 126.56 |
| NYT Connections (extended) | 92.1% | — |
| ARC-AGI-1 | 94% | — |
| EnigmaEval | 7.6% | — |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |
| LiveBench Reasoning | — | 32.8% |
| LiveBench Data Analysis | — | 50% |
| ForecastBench | 60 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- Claude Opus 4.6: 63.0 (#31)
- GPT-4o mini: 10.4 (#314)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 0.7% |
| OTIS Mock AIME 2024-2025 | 94.4% | 6.9% |
| LMArena Math | 1519 | 1267 |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 78.5% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |
| GSM8K | — | 91.3% |

## Knowledge

- Claude Opus 4.6: 61.9 (#26)
- GPT-4o mini: 17.7 (#284)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 90.5% | 37.7% |
| SimpleQA Verified | 47% | 8.3% |
| LMArena Expert | 1546 | 1235 |
| Humanity's Last Exam | 34.4% | — |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| Vectara Hallucination Rate | 12.2% | — |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- Claude Opus 4.6: 37.3 (#74)
- GPT-4o mini: 25.9 (#122)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1316 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |

## Multilingual

- Claude Opus 4.6: 57.9 (#6)
- GPT-4o mini: 42.0 (#199)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1489 | 1266 |
| LMArena Chinese | 1551 | 1265 |
| LMArena French | 1513 | 1297 |
| LMArena German | 1502 | 1272 |
| LMArena Japanese | 1484 | 1216 |
| LMArena Korean | 1464 | 1195 |
| LMArena Russian | 1497 | 1275 |
| LMArena Spanish | 1510 | 1276 |

## Instruction Following

- Claude Opus 4.6: 79.5 (#4)
- GPT-4o mini: 61.9 (#239)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1523 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |

## Long Context

- Claude Opus 4.6: 48.1 (#13)
- GPT-4o mini: 39.1 (#186)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1520 | 1289 |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |

## Writing & Preference

- Claude Opus 4.6: 73.5 (#10)
- GPT-4o mini: 39.5 (#248)

| Benchmark | Claude Opus 4.6 | GPT-4o mini |
|---|---|---|
| LMArena Text | 1503 | 1286 |
| LMArena Creative Writing | 1505 | 1268 |
| EQ-Bench Creative Writing | 1809 | 873 |
| LMArena Multi-Turn | 1513 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| WildBench | — | 79.1% |
| EQ-Bench 4 | 1223 | — |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Claude Opus 4.6 better than GPT-4o mini?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 25.5 on the Noometry Index. GPT-4o mini costs 38× 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-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

### Is Claude Opus 4.6 or GPT-4o mini better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 22.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 128K.

### How many benchmarks do Claude Opus 4.6 and GPT-4o mini share?

32 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GPT-4o mini has 60.