Model comparison
Claude Opus 5 vs o3-mini
Claude Opus 5 is the stronger model overall, scoring 67.8 to 36.7 on the Noometry Index. o3-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 . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and o3-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 16.3.
- The biggest single-benchmark swing is ARC-AGI-2: 90.4% for Claude Opus 5 and 3% for o3-mini.
- o3-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 | o3-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 67.8 | 36.7 |
| Released | 2026-07-24 | 2024-12-20 |
| 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 | 51 |
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), o3-mini: 40.8 (#132)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| SciCode | 56.4% | 39.8% |
| WeirdML | 91.8% | 43.7% |
| LMArena Coding | 1534 | 1378 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| Aider Polyglot | — | 60.4% |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
| GSO | — | 1.3% |
| LiveBench Coding | — | 82.7% |
| CadEval | — | 54% |
| ALE-Bench | 2,165 | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), o3-mini: 29.6 (#84)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| APEX-Agents | 65.8% | — |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| Cybench | — | 22.5% |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), o3-mini: 16.3 (#305)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| ARC-AGI-2 | 90.4% | 3% |
| SimpleBench | 80.6% | 22.8% |
| ARC-AGI-1 | 97.5% | 34.5% |
| CritPt | 29.1% | 0.3% |
| Chess Puzzles | 42% | 17% |
| LMArena Hard Prompts | 1526 | 1366 |
| Mystery Game Puzzles | 59% | 7% |
| DTBench | 97.9% | 68.8% |
| LMCA | 64.5% | 19% |
| Epoch Capabilities Index | 162.78 | 140.34 |
| NYT Connections (extended) | 94.3% | — |
| EBR-Bench | 45.7% | — |
| LiveBench Reasoning | — | 89.6% |
| LiveBench Data Analysis | — | 70.6% |
| Bench to the Future 3 | 0.12 | — |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), o3-mini: 28.1 (#244)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 18.6% |
| FrontierMath Tier 4 | 73.2% | 0% |
| OTIS Mock AIME 2024-2025 | 98.9% | 76.9% |
| LMArena Math | 1531 | 1396 |
| ProofBench | 99% | — |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), o3-mini: 38.3 (#146)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| GPQA Diamond | 93.9% | 77% |
| SimpleQA Verified | 59.9% | 15.3% |
| LMArena Expert | 1557 | 1364 |
| Confabulations | — | 17.9% |
Multimodal Not comparable
Claude Opus 5: 50.8 (#8), o3-mini: —
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), o3-mini: 45.7 (#164)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| LMArena Non-English | 1501 | 1319 |
| LMArena Chinese | 1574 | 1379 |
| LMArena French | 1519 | 1334 |
| LMArena German | 1524 | 1303 |
| LMArena Japanese | 1516 | 1286 |
| LMArena Korean | 1521 | 1314 |
| LMArena Russian | 1507 | 1304 |
| LMArena Spanish | 1519 | 1321 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), o3-mini: 75.1 (#72)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1517 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), o3-mini: 33.8 (#256)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1515 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), o3-mini: 50.3 (#182)
| Benchmark | Claude Opus 5 | o3-mini |
|---|---|---|
| LMArena Text | 1507 | 1337 |
| LMArena Creative Writing | 1491 | 1286 |
| LMArena Multi-Turn | 1499 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Claude Opus 5 better than o3-mini?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 36.7 on the Noometry Index. o3-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 o3-mini?
o3-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 o3-mini better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 40.8 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 o3-mini share?
33 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and o3-mini has 51.