Model comparison
Claude Sonnet 5 vs GPT-5 Mini
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 41.7 on the Noometry Index. GPT-5 Mini costs 5.8× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. Claude Sonnet 5 scores higher in 10 categories and GPT-5 Mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 48.2 to 24.1.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 9% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Sonnet 5 | GPT-5 Mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.5 | 41.7 |
| Released | 2026-06-29 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $10 | $2 |
| Results tracked | 51 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#20), GPT-5 Mini: 40.0 (#134)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| SciCode | 53.6% | 39.2% |
| WeirdML | 68.8% | 52.7% |
| LMArena Coding | 1483 | 1406 |
| ALE-Bench | 1,463 | 799.77 |
| SWE-bench Verified | — | 64.7% |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 59.8% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1540 | — |
| SWE-bench Multilingual | — | 39.7% |
| GSO | 37.3% | — |
| AlgoTune | — | 1.38 |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.7 (#16), GPT-5 Mini: 31.0 (#64)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| Vending-Bench 2 | 6,378 | -31.18 |
| Terminal-Bench | — | 34.8% |
| APEX-Agents | 54.5% | — |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 48.2 (#37), GPT-5 Mini: 24.1 (#153)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| CritPt | 16.9% | 0% |
| Chess Puzzles | 35% | 30% |
| LMArena Hard Prompts | 1461 | 1380 |
| Mystery Game Puzzles | 35% | 10% |
| DTBench | 92.5% | 80.5% |
| LMCA | 50% | 34.2% |
| Epoch Capabilities Index | 156.34 | 145.51 |
| ForecastBench | 61.1 | 61 |
| ARC-AGI-2 | — | 4.4% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 70.3% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 54.3% |
| EnigmaEval | — | 8.2% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.1 (#21), GPT-5 Mini: 46.3 (#59)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 46.7% |
| FrontierMath Tier 4 | 29.3% | 12.2% |
| OTIS Mock AIME 2024-2025 | 94.7% | 86.7% |
| ProofBench | 77% | 9% |
| LMArena Math | 1467 | 1377 |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 27.2% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.7 (#42), GPT-5 Mini: 45.5 (#80)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 90.5% | 75% |
| SimpleQA Verified | 33.7% | 21.6% |
| LMArena Expert | 1491 | 1377 |
| Humanity's Last Exam | — | 19.4% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |
| GPQA (HELM) | — | 75.6% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#26), GPT-5 Mini: 35.0 (#80)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1275 | 1202 |
| VPCT | — | 40.2% |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 54.0 (#55), GPT-5 Mini: 49.1 (#131)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1431 | 1363 |
| LMArena Chinese | 1475 | 1387 |
| LMArena French | 1457 | 1385 |
| LMArena German | 1448 | 1366 |
| LMArena Japanese | 1422 | 1342 |
| LMArena Korean | 1411 | 1306 |
| LMArena Russian | 1452 | 1362 |
| LMArena Spanish | 1436 | 1355 |
Instruction Following Too close to call
Claude Sonnet 5: 76.6 (#39), GPT-5 Mini: 76.4 (#43)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1453 | 1357 |
| IFEval | — | 92.7% |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#53), GPT-5 Mini: 41.9 (#127)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1464 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.4 (#24), GPT-5 Mini: 55.4 (#143)
| Benchmark | Claude Sonnet 5 | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1443 | 1373 |
| LMArena Creative Writing | 1416 | 1325 |
| EQ-Bench Creative Writing | 1794 | 1313 |
| LMArena Multi-Turn | 1454 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| WildBench | — | 85.5% |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than GPT-5 Mini?
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 41.7 on the Noometry Index. GPT-5 Mini costs 5.8× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or GPT-5 Mini?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or GPT-5 Mini better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 40.0 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 400K.
How many benchmarks do Claude Sonnet 5 and GPT-5 Mini share?
36 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-5 Mini has 60.