Model comparison
Claude Sonnet 5 vs GPT-5.4 nano
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 41.9 on the Noometry Index. GPT-5.4 nano costs 8.6× less per token, which makes it the better buy when Claude Sonnet 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 Sonnet 5 scores higher in 9 categories and GPT-5.4 nano in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 40.7.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 5% for GPT-5.4 nano.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 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-5.4 nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.5 | 41.9 |
| Released | 2026-06-29 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $0.20 |
| Output $ / M tokens | $10 | $1.25 |
| Results tracked | 51 | 40 |
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-5.4 nano: 43.1 (#82)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| SciCode | 53.6% | 46.9% |
| WeirdML | 68.8% | 49.2% |
| LMArena Coding | 1483 | 1404 |
| ALE-Bench | 1,463 | 1,005 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1540 | — |
| GSO | 37.3% | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.7 (#16), GPT-5.4 nano: —
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 48.2 (#37), GPT-5.4 nano: 23.8 (#159)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| CritPt | 16.9% | 9.3% |
| Chess Puzzles | 35% | 30% |
| LMArena Hard Prompts | 1461 | 1380 |
| Mystery Game Puzzles | 35% | 9% |
| DTBench | 92.5% | 80.3% |
| LMCA | 50% | 36.9% |
| Epoch Capabilities Index | 156.34 | 145.78 |
| ForecastBench | 61.1 | 57.3 |
| ARC-AGI-2 | — | 5.7% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 39.7% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 51.5% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.1 (#21), GPT-5.4 nano: 40.7 (#76)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 44.9% |
| FrontierMath Tier 4 | 29.3% | 12.2% |
| OTIS Mock AIME 2024-2025 | 94.7% | 87.8% |
| ProofBench | 77% | 5% |
| LMArena Math | 1467 | 1406 |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.7 (#42), GPT-5.4 nano: 41.8 (#94)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 90.5% | 78.5% |
| SimpleQA Verified | 33.7% | 11.7% |
| LMArena Expert | 1491 | 1397 |
| Vectara Hallucination Rate | — | 3.1% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#26), GPT-5.4 nano: 36.0 (#73)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | 1275 | 1196 |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 54.0 (#55), GPT-5.4 nano: 48.8 (#136)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1431 | 1359 |
| LMArena Chinese | 1475 | 1391 |
| LMArena French | 1457 | 1396 |
| LMArena German | 1448 | 1368 |
| LMArena Japanese | 1422 | 1342 |
| LMArena Korean | 1411 | 1321 |
| LMArena Russian | 1452 | 1363 |
| LMArena Spanish | 1436 | 1368 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.6 (#39), GPT-5.4 nano: 72.1 (#139)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1453 | 1362 |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#53), GPT-5.4 nano: 41.6 (#131)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1464 | 1365 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.4 (#24), GPT-5.4 nano: 55.9 (#137)
| Benchmark | Claude Sonnet 5 | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1443 | 1372 |
| LMArena Creative Writing | 1416 | 1313 |
| LMArena Multi-Turn | 1454 | 1382 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than GPT-5.4 nano?
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 41.9 on the Noometry Index. GPT-5.4 nano costs 8.6× 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-5.4 nano?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or GPT-5.4 nano better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 43.1 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-5.4 nano share?
34 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-5.4 nano has 40.