Model comparison
Claude Sonnet 5 vs GPT-5 Nano
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 33.4 on the Noometry Index. GPT-5 Nano costs 29× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude Sonnet 5 scores higher in 10 categories and GPT-5 Nano in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 29.1.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 12% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 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 Nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.5 | 33.4 |
| Released | 2026-06-29 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $0.05 |
| Output $ / M tokens | $10 | $0.40 |
| Results tracked | 51 | 48 |
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 Nano: 33.3 (#248)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| WeirdML | 68.8% | 38.1% |
| LMArena Coding | 1483 | 1351 |
| ALE-Bench | 1,463 | 718.67 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 34.8% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1540 | — |
| SciCode | 53.6% | — |
| GSO | 37.3% | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.7 (#16), GPT-5 Nano: 25.6 (#99)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| APEX-Agents | 54.5% | — |
| Berkeley Function Calling Leaderboard | — | 51.5% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 48.2 (#37), GPT-5 Nano: 16.4 (#291)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| Chess Puzzles | 35% | 27% |
| LMArena Hard Prompts | 1461 | 1329 |
| Mystery Game Puzzles | 35% | 9% |
| DTBench | 92.5% | 62.7% |
| LMCA | 50% | 7.9% |
| Epoch Capabilities Index | 156.34 | 139.39 |
| ForecastBench | 61.1 | 59.1 |
| ARC-AGI-2 | — | 2.6% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 62.2% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 20.7% |
| CritPt | 16.9% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.1 (#21), GPT-5 Nano: 29.1 (#221)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 20% |
| FrontierMath Tier 4 | 29.3% | 2.4% |
| OTIS Mock AIME 2024-2025 | 94.7% | 81.1% |
| ProofBench | 77% | 12% |
| LMArena Math | 1467 | 1318 |
| Omni-MATH | — | 54.6% |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.7 (#42), GPT-5 Nano: 35.8 (#166)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 90.5% | 69.4% |
| SimpleQA Verified | 33.7% | 11.7% |
| LMArena Expert | 1491 | 1321 |
| MMLU-Pro | — | 77.8% |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | — | 67.9% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#26), GPT-5 Nano: 30.7 (#102)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1275 | 1159 |
| VPCT | — | 37.2% |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 54.0 (#55), GPT-5 Nano: 45.5 (#167)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1431 | 1313 |
| LMArena Chinese | 1475 | 1355 |
| LMArena German | 1448 | 1329 |
| LMArena Korean | 1411 | 1269 |
| LMArena Russian | 1452 | 1296 |
| LMArena Spanish | 1436 | 1360 |
| LMArena French | 1457 | — |
| LMArena Japanese | 1422 | — |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.6 (#39), GPT-5 Nano: 75.2 (#72)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1453 | 1306 |
| IFEval | — | 93.2% |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#53), GPT-5 Nano: 31.3 (#275)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1464 | 1313 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.4 (#24), GPT-5 Nano: 39.4 (#244)
| Benchmark | Claude Sonnet 5 | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1443 | 1320 |
| LMArena Creative Writing | 1416 | 1250 |
| EQ-Bench Creative Writing | 1794 | 705 |
| LMArena Multi-Turn | 1454 | 1311 |
| WildBench | — | 80.6% |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than GPT-5 Nano?
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 33.4 on the Noometry Index. GPT-5 Nano costs 29× 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 Nano?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or GPT-5 Nano better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 33.3 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 Nano share?
31 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-5 Nano has 48.