# Claude Opus 5.5 vs o4-mini

> Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 41.6 on the Noometry Index. o4-mini costs 4.2× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-5-5-vs-o4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude Opus 5.5 scores higher in 10 categories and o4-mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 79.5 to 24.6.
- The biggest single-benchmark swing is FrontierMath Tier 4: 95% for Claude Opus 5.5 and 4.9% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 200K.

## Snapshot

| | Claude Opus 5.5 | o4-mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.5 | 41.6 |
| Rank | 3 | 119 |
| Context | 1M | 200K |
| Input $/M | $4 | $1.10 |
| Output $/M | $20 | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 5.5: 71.4 (#1)
- o4-mini: 41.6 (#110)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| LMArena Coding | 1545 | 1369 |
| FrontierCode | 54.4% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| CursorBench | 57.8% | — |
| LMArena WebDev | 1820 | — |
| FrontierSWE | 62.3% | — |
| SciCode | 66.9% | — |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| MirrorCode | 77.4% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |

## Agentic & Tool Use

- Claude Opus 5.5: 45.3 (#13)
- o4-mini: 32.3 (#57)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| APEX-Agents | 73.5% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| GDP.pdf | 30.6% | — |
| METR Time Horizons | — | 63.9% |

## Reasoning

- Claude Opus 5.5: 79.5 (#2)
- o4-mini: 24.6 (#143)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 92.5% | 6.1% |
| ARC-AGI-1 | 97.5% | 58.7% |
| CritPt | 31.7% | 0.6% |
| LMArena Hard Prompts | 1545 | 1351 |
| Mystery Game Puzzles | 71% | 5% |
| DTBench | 98.9% | 77.6% |
| LMCA | 68.2% | 26.5% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 88.5% | — |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| EBR-Bench | 71.4% | — |
| Epoch Capabilities Index | — | 145.63 |
| ForecastBench | — | 61.8 |

## Math

- Claude Opus 5.5: 92.4 (#2)
- o4-mini: 40.2 (#79)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 91.2% | 36.1% |
| FrontierMath Tier 4 | 95% | 4.9% |
| OTIS Mock AIME 2024-2025 | 100% | 81.7% |
| ProofBench | 100% | — |
| Omni-MATH | — | 72% |
| LMArena Math | — | 1390 |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |

## Knowledge

- Claude Opus 5.5: 66.6 (#9)
- o4-mini: 43.5 (#83)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| GPQA Diamond | 90.6% | 79.6% |
| SimpleQA Verified | 72.2% | 19.6% |
| LMArena Expert | 1564 | 1344 |
| Humanity's Last Exam | — | 18.1% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |

## Multimodal

- Claude Opus 5.5: 56.5 (#2)
- o4-mini: 39.5 (#46)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| LMArena Vision | — | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Furniture Assembly | 83.3% | — |

## Multilingual

- Claude Opus 5.5: 59.8 (#1)
- o4-mini: 47.2 (#149)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| LMArena Non-English | 1513 | 1336 |
| LMArena Chinese | 1572 | 1355 |
| LMArena Russian | 1532 | 1334 |
| LMArena French | — | 1362 |
| LMArena German | — | 1336 |
| LMArena Japanese | — | 1308 |
| LMArena Korean | — | 1313 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- Claude Opus 5.5: 80.1 (#2)
- o4-mini: 75.4 (#63)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1535 | 1321 |
| IFEval | — | 92.8% |

## Long Context

- Claude Opus 5.5: 47.3 (#18)
- o4-mini: 45.5 (#31)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1540 | 1315 |
| Fiction.LiveBench | — | 77.8% |

## Writing & Preference

- Claude Opus 5.5: 78.7 (#3)
- o4-mini: 54.2 (#148)

| Benchmark | Claude Opus 5.5 | o4-mini |
|---|---|---|
| LMArena Text | 1518 | 1353 |
| LMArena Creative Writing | 1538 | 1294 |
| LMArena Multi-Turn | 1520 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 2050 | — |
| WildBench | — | 85.4% |

## FAQ

### Is Claude Opus 5.5 better than o4-mini?

Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 41.6 on the Noometry Index. o4-mini costs 4.2× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 5.5 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 5.5 lists at $4 and $20.

### Is Claude Opus 5.5 or o4-mini better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.4 versus 41.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 200K.

### How many benchmarks do Claude Opus 5.5 and o4-mini share?

22 benchmarks have published results for both models. Claude Opus 5.5 has 35 scored results on Noometry and o4-mini has 60.