Model comparison
Claude 3.5 Sonnet vs GPT-5 Mini
GPT-5 Mini is the stronger model overall, scoring 41.7 to 34.4 on the Noometry Index.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 1 category and GPT-5 Mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.3 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 86.7% for GPT-5 Mini.
Side by side
| Claude 3.5 Sonnet | GPT-5 Mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.4 | 41.7 |
| Released | 2024-06-20 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $2 |
| Results tracked | 60 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude 3.5 Sonnet: 39.5 (#145), GPT-5 Mini: 40.0 (#134)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| WeirdML | 40% | 52.7% |
| LMArena Coding | 1343 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| Aider Polyglot | 51.6% | — |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.1 (#61), GPT-5 Mini: 31.0 (#64)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5 Mini leads
Claude 3.5 Sonnet: 22.5 (#176), GPT-5 Mini: 24.1 (#153)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| EnigmaEval | 0.9% | 8.2% |
| LMArena Hard Prompts | 1305 | 1380 |
| DTBench | 67.8% | 80.5% |
| Epoch Capabilities Index | 133.55 | 145.51 |
| ForecastBench | 60.7 | 61 |
| ARC-AGI-2 | — | 4.4% |
| SimpleBench | 41.4% | — |
| Kagi LLM Benchmark | — | 70.3% |
| ARC-AGI-1 | — | 54.3% |
| CritPt | — | 0% |
| Chess Puzzles | — | 30% |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 10% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 34.2% |
| LiveBench | 59% | — |
Math GPT-5 Mini leads
Claude 3.5 Sonnet: 18.0 (#282), GPT-5 Mini: 46.3 (#59)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 86.7% |
| Omni-MATH | 27.6% | 72.2% |
| LMArena Math | 1306 | 1377 |
| MATH Level 5 | 56.9% | 97.8% |
| FrontierMath (Feb 2025 set) | 2.1% | 27.2% |
| FrontierMath Tier 4 (v1) | 0% | 6.3% |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 9% |
| LiveBench Math | 52.3% | — |
Knowledge GPT-5 Mini leads
Claude 3.5 Sonnet: 28.5 (#236), GPT-5 Mini: 45.5 (#80)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 55.3% | 75% |
| Humanity's Last Exam | 4.1% | 19.4% |
| MMLU-Pro | 77.7% | 83.5% |
| Confabulations | 19.9% | 13.3% |
| GPQA (HELM) | 56.5% | 75.6% |
| LMArena Expert | 1264 | 1377 |
| SimpleQA Verified | — | 21.6% |
| Vectara Hallucination Rate | — | 12.9% |
| MMLU | 87.3% | — |
Multimodal GPT-5 Mini leads
Claude 3.5 Sonnet: 26.0 (#115), GPT-5 Mini: 35.0 (#80)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1125 | 1202 |
| VPCT | 33% | 40.2% |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
Multilingual GPT-5 Mini leads
Claude 3.5 Sonnet: 43.4 (#180), GPT-5 Mini: 49.1 (#131)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1283 | 1363 |
| LMArena Chinese | 1271 | 1387 |
| LMArena French | 1304 | 1385 |
| LMArena German | 1297 | 1366 |
| LMArena Japanese | 1234 | 1342 |
| LMArena Korean | 1200 | 1306 |
| LMArena Russian | 1305 | 1362 |
| LMArena Spanish | 1289 | 1355 |
Instruction Following GPT-5 Mini leads
Claude 3.5 Sonnet: 69.0 (#177), GPT-5 Mini: 76.4 (#43)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| IFEval | 85.5% | 92.7% |
| LMArena Instruction Following | 1297 | 1357 |
| LiveBench Instruction Following | 69.3% | — |
Long Context GPT-5 Mini leads
Claude 3.5 Sonnet: 39.9 (#162), GPT-5 Mini: 41.9 (#127)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1311 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference GPT-5 Mini leads
Claude 3.5 Sonnet: 53.0 (#159), GPT-5 Mini: 55.4 (#143)
| Benchmark | Claude 3.5 Sonnet | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1298 | 1373 |
| LMArena Creative Writing | 1292 | 1325 |
| Short-Story Creative Writing | 80.3% | 83.1% |
| EQ-Bench Creative Writing | 1451 | 1313 |
| WildBench | 79.2% | 85.5% |
| LMArena Multi-Turn | 1326 | 1363 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than GPT-5 Mini?
GPT-5 Mini is the stronger model overall, scoring 41.7 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or GPT-5 Mini better for coding?
They score almost the same on coding (39.5 vs 40.0); test both on your own repository before choosing.
How many benchmarks do Claude 3.5 Sonnet and GPT-5 Mini share?
38 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and GPT-5 Mini has 60.