Model comparison
Claude Opus 5 vs o4-mini
Claude Opus 5 is the stronger model overall, scoring 67.8 to 41.6 on the Noometry Index. o4-mini costs 5.2× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Claude Opus 5 scores higher in 10 categories and o4-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 24.6.
- The biggest single-benchmark swing is ARC-AGI-2: 90.4% for Claude Opus 5 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 5.
- Claude Opus 5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Opus 5 | o4-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 67.8 | 41.6 |
| Released | 2026-07-24 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $5 | $1.10 |
| Output $ / M tokens | $25 | $4.40 |
| Results tracked | 57 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), o4-mini: 40.9 (#127)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| WeirdML | 91.8% | 52.6% |
| LMArena Coding | 1534 | 1368 |
| ALE-Bench | 2,165 | 826.17 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
| SciCode | 56.4% | — |
| GSO | — | 3.6% |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), o4-mini: 32.6 (#61)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| APEX-Agents | 65.8% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| OSWorld 2.0 | 31.4% | — |
| GDPval | — | 25.3% |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), o4-mini: 24.6 (#162)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 90.4% | 6.1% |
| SimpleBench | 80.6% | 38.7% |
| ARC-AGI-1 | 97.5% | 58.7% |
| CritPt | 29.1% | 0.6% |
| Chess Puzzles | 42% | 26% |
| LMArena Hard Prompts | 1526 | 1351 |
| Mystery Game Puzzles | 59% | 5% |
| DTBench | 97.9% | 77.6% |
| LMCA | 64.5% | 26.5% |
| Epoch Capabilities Index | 162.78 | 145.64 |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 94.3% | — |
| EnigmaEval | — | 9.2% |
| EBR-Bench | 45.7% | — |
| Bench to the Future 3 | 0.12 | — |
| ForecastBench | — | 61.8 |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), o4-mini: 40.8 (#89)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 36.1% |
| FrontierMath Tier 4 | 73.2% | 4.9% |
| OTIS Mock AIME 2024-2025 | 98.9% | 81.7% |
| LMArena Math | 1531 | 1389 |
| ProofBench | 99% | — |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), o4-mini: 43.6 (#91)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| GPQA Diamond | 93.9% | 79.6% |
| SimpleQA Verified | 59.9% | 19.6% |
| LMArena Expert | 1557 | 1343 |
| 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 leads
Claude Opus 5: 50.8 (#8), o4-mini: 40.2 (#49)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| LMArena Vision | 1319 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), o4-mini: 47.0 (#154)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| LMArena Non-English | 1501 | 1337 |
| LMArena Chinese | 1574 | 1354 |
| LMArena French | 1519 | 1364 |
| LMArena German | 1524 | 1336 |
| LMArena Japanese | 1516 | 1308 |
| LMArena Korean | 1521 | 1312 |
| LMArena Russian | 1507 | 1334 |
| LMArena Spanish | 1519 | 1347 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), o4-mini: 75.2 (#68)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1517 | 1321 |
| IFEval | — | 92.8% |
Long Context Too close to call
Claude Opus 5: 46.5 (#21), o4-mini: 45.5 (#33)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1515 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), o4-mini: 54.0 (#152)
| Benchmark | Claude Opus 5 | o4-mini |
|---|---|---|
| LMArena Text | 1507 | 1353 |
| LMArena Creative Writing | 1491 | 1294 |
| LMArena Multi-Turn | 1499 | 1350 |
| Short-Story Creative Writing | — | 75% |
| EQ-Bench Creative Writing | 2133 | — |
| WildBench | — | 85.4% |
| EQ-Bench 4 | 1385 | — |
Frequently asked questions
Is Claude Opus 5 better than o4-mini?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 41.6 on the Noometry Index. o4-mini costs 5.2× 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 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 lists at $5 and $25.
Is Claude Opus 5 or o4-mini better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 200K.
How many benchmarks do Claude Opus 5 and o4-mini share?
34 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and o4-mini has 60.