# Claude Opus 4.6 vs o4-mini

> Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 41.6 on the Noometry Index. o4-mini costs 5.2× 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-o4-mini
- Last updated: 2026-10-11
- Shared benchmarks: 44

## Summary

- They share 44 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and o4-mini in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 24.6.
- The biggest single-benchmark swing is ARC-AGI-2: 69.2% for Claude Opus 4.6 and 6.1% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
- Claude Opus 4.6 accepts more context: 1M tokens versus 200K.

## Snapshot

| | Claude Opus 4.6 | o4-mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.2 | 41.6 |
| Rank | 20 | 132 |
| Context | 1M | 200K |
| Input $/M | $5 | $1.10 |
| Output $/M | $25 | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.6: 57.2 (#20)
- o4-mini: 40.9 (#127)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 75.6% | 45% |
| GSO | 41.2% | 3.6% |
| WeirdML | 78% | 52.6% |
| LMArena Coding | 1536 | 1368 |
| ALE-Bench | 996.5 | 826.17 |
| AlgoTune | 1.47 | 1.72 |
| SWE-bench Verified | 78.7% | — |
| FrontierCode | 26.6% | — |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1547 | — |
| SWE-bench Multilingual | 72% | — |
| CadEval | — | 62% |

## Agentic & Tool Use

- Claude Opus 4.6: 51.1 (#4)
- o4-mini: 32.6 (#61)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| METR Time Horizons | 78.9% | 63.9% |
| Terminal-Bench | 79.8% | — |
| APEX-Agents | 46.3% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| GBAEval | 44.1% | — |
| LMArena Search | 1253 | — |
| Vending-Bench 2 | 8,018 | — |

## Reasoning

- Claude Opus 4.6: 57.8 (#23)
- o4-mini: 24.6 (#162)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 69.2% | 6.1% |
| SimpleBench | 67.6% | 38.7% |
| Kagi LLM Benchmark | 83.6% | 67.6% |
| ARC-AGI-1 | 94% | 58.7% |
| Chess Puzzles | 17% | 26% |
| EnigmaEval | 7.6% | 9.2% |
| LMArena Hard Prompts | 1527 | 1351 |
| Mystery Game Puzzles | 25% | 5% |
| DTBench | 91.2% | 77.6% |
| LMCA | 55.8% | 26.5% |
| Epoch Capabilities Index | 155.24 | 145.64 |
| ForecastBench | 60 | 61.8 |
| NYT Connections (extended) | 92.1% | — |
| CritPt | — | 0.6% |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |

## Math

- Claude Opus 4.6: 63.0 (#31)
- o4-mini: 40.8 (#89)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 36.1% |
| FrontierMath Tier 4 | 26.8% | 4.9% |
| OTIS Mock AIME 2024-2025 | 94.4% | 81.7% |
| LMArena Math | 1519 | 1389 |
| FrontierMath (Feb 2025 set) | 40.7% | 24.8% |
| FrontierMath Tier 4 (v1) | 22.9% | 6.3% |
| MathArena Final-Answer Competitions | 78.5% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |

## Knowledge

- Claude Opus 4.6: 61.9 (#26)
- o4-mini: 43.6 (#91)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| GPQA Diamond | 90.5% | 79.6% |
| Humanity's Last Exam | 34.4% | 18.1% |
| SimpleQA Verified | 47% | 19.6% |
| Vectara Hallucination Rate | 12.2% | 18.6% |
| LMArena Expert | 1546 | 1343 |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| GPQA (HELM) | — | 73.5% |

## Multimodal

- Claude Opus 4.6: 37.3 (#74)
- o4-mini: 40.2 (#49)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| LMArena Vision | 1316 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |

## Multilingual

- Claude Opus 4.6: 57.9 (#6)
- o4-mini: 47.0 (#154)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| LMArena Non-English | 1489 | 1337 |
| LMArena Chinese | 1551 | 1354 |
| LMArena French | 1513 | 1364 |
| LMArena German | 1502 | 1336 |
| LMArena Japanese | 1484 | 1308 |
| LMArena Korean | 1464 | 1312 |
| LMArena Russian | 1497 | 1334 |
| LMArena Spanish | 1510 | 1347 |

## Instruction Following

- Claude Opus 4.6: 79.5 (#4)
- o4-mini: 75.2 (#68)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1523 | 1321 |
| IFEval | — | 92.8% |

## Long Context

- Claude Opus 4.6: 48.1 (#13)
- o4-mini: 45.5 (#33)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1520 | 1315 |
| Fiction.LiveBench | — | 77.8% |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |

## Writing & Preference

- Claude Opus 4.6: 73.5 (#10)
- o4-mini: 54.0 (#152)

| Benchmark | Claude Opus 4.6 | o4-mini |
|---|---|---|
| LMArena Text | 1503 | 1353 |
| LMArena Creative Writing | 1505 | 1294 |
| LMArena Multi-Turn | 1513 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 1809 | — |
| WildBench | — | 85.4% |
| EQ-Bench 4 | 1223 | — |

## FAQ

### Is Claude Opus 4.6 better than o4-mini?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 41.6 on the Noometry Index. o4-mini costs 5.2× 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 o4-mini?

o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

### Is Claude Opus 4.6 or o4-mini better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 40.9 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 200K.

### How many benchmarks do Claude Opus 4.6 and o4-mini share?

44 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and o4-mini has 60.