Model comparison
Claude Opus 4.6 vs GPT-5.4 mini
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 45.0 on the Noometry Index. GPT-5.4 mini costs 5.9× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and GPT-5.4 mini in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 30.4.
- The biggest single-benchmark swing is ARC-AGI-2: 69.2% for Claude Opus 4.6 and 18.9% for GPT-5.4 mini.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
- Claude Opus 4.6 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Opus 4.6 | GPT-5.4 mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.2 | 45.0 |
| Released | 2026-02-04 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $0.75 |
| Output $ / M tokens | $25 | $4.50 |
| Results tracked | 68 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.6 leads
Claude Opus 4.6: 57.2 (#20), GPT-5.4 mini: 45.2 (#72)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| FrontierCode | 26.6% | 27% |
| LMArena WebDev | 1547 | 1397 |
| WeirdML | 78% | 60.3% |
| LMArena Coding | 1536 | 1438 |
| ALE-Bench | 996.5 | 1,189 |
| SWE-bench Verified | 78.7% | — |
| SWE-bench Verified (bash only) | 75.6% | — |
| SWE-bench Multilingual | 72% | — |
| SciCode | — | 49.9% |
| GSO | 41.2% | — |
| AlgoTune | 1.47 | — |
Agentic & Tool Use Claude Opus 4.6 leads
Claude Opus 4.6: 51.1 (#4), GPT-5.4 mini: 29.9 (#81)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | 55.3% | 36.3% |
| Terminal-Bench | 79.8% | — |
| APEX-Agents | 46.3% | — |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| GBAEval | 44.1% | — |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |
| Vending-Bench 2 | 8,018 | — |
Reasoning Claude Opus 4.6 leads
Claude Opus 4.6: 57.8 (#23), GPT-5.4 mini: 30.4 (#85)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 69.2% | 18.9% |
| Kagi LLM Benchmark | 83.6% | 37.9% |
| NYT Connections (extended) | 92.1% | 61.8% |
| ARC-AGI-1 | 94% | 63.7% |
| Chess Puzzles | 17% | 24% |
| Thematic Generalization | 80.6% | 61.7% |
| LMArena Hard Prompts | 1527 | 1424 |
| Mystery Game Puzzles | 25% | 11% |
| DTBench | 91.2% | 80% |
| LMCA | 55.8% | 40.8% |
| Epoch Capabilities Index | 155.24 | 148.84 |
| ForecastBench | 60 | 57 |
| SimpleBench | 67.6% | — |
| CritPt | — | 10% |
| EnigmaEval | 7.6% | — |
| EBR-Bench | 12.7% | — |
Math Claude Opus 4.6 leads
Claude Opus 4.6: 63.0 (#31), GPT-5.4 mini: 45.5 (#75)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 51.2% |
| FrontierMath Tier 4 | 26.8% | 9.8% |
| OTIS Mock AIME 2024-2025 | 94.4% | 88.9% |
| ProofBench | 50% | 21% |
| LMArena Math | 1519 | 1419 |
| FrontierMath (Feb 2025 set) | 40.7% | 28.3% |
| FrontierMath Tier 4 (v1) | 22.9% | 2.1% |
| MathArena Final-Answer Competitions | 78.5% | — |
Knowledge Claude Opus 4.6 leads
Claude Opus 4.6: 61.9 (#26), GPT-5.4 mini: 51.5 (#67)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 90.5% | 86.9% |
| SimpleQA Verified | 47% | 29.4% |
| Vectara Hallucination Rate | 12.2% | 5.5% |
| LMArena Expert | 1546 | 1435 |
| Humanity's Last Exam | 34.4% | — |
Multimodal GPT-5.4 mini leads
Claude Opus 4.6: 37.3 (#74), GPT-5.4 mini: 39.7 (#56)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1316 | 1245 |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |
Multilingual Claude Opus 4.6 leads
Claude Opus 4.6: 57.9 (#6), GPT-5.4 mini: 51.9 (#96)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1489 | 1405 |
| LMArena Chinese | 1551 | 1446 |
| LMArena French | 1513 | 1440 |
| LMArena German | 1502 | 1409 |
| LMArena Japanese | 1484 | 1374 |
| LMArena Korean | 1464 | 1368 |
| LMArena Russian | 1497 | 1417 |
| LMArena Spanish | 1510 | 1405 |
Instruction Following Claude Opus 4.6 leads
Claude Opus 4.6: 79.5 (#4), GPT-5.4 mini: 74.1 (#102)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1523 | 1405 |
Long Context Claude Opus 4.6 leads
Claude Opus 4.6: 48.1 (#13), GPT-5.4 mini: 43.0 (#112)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1520 | 1407 |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |
Writing & Preference Claude Opus 4.6 leads
Claude Opus 4.6: 73.5 (#10), GPT-5.4 mini: 64.0 (#58)
| Benchmark | Claude Opus 4.6 | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1503 | 1412 |
| LMArena Creative Writing | 1505 | 1370 |
| EQ-Bench Creative Writing | 1809 | 1665 |
| LMArena Multi-Turn | 1513 | 1429 |
| EQ-Bench 4 | 1223 | — |
Frequently asked questions
Is Claude Opus 4.6 better than GPT-5.4 mini?
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 45.0 on the Noometry Index. GPT-5.4 mini costs 5.9× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.6 or GPT-5.4 mini?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Claude Opus 4.6 lists at $5 and $25.
Is Claude Opus 4.6 or GPT-5.4 mini better for coding?
Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 45.2 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4.6 does, with 1M tokens against 400K.
How many benchmarks do Claude Opus 4.6 and GPT-5.4 mini share?
44 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GPT-5.4 mini has 46.