Model comparison
Claude Opus 5 vs GPT-4 Turbo
Claude Opus 5 is the stronger model overall, scoring 67.8 to 30.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and GPT-4 Turbo in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.2 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Claude Opus 5 and 6.7% for GPT-4 Turbo.
- Claude Opus 5 is cheaper at $5 / $25 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Claude Opus 5 accepts more context: 1M tokens versus 128K.
Side by side
| Claude Opus 5 | GPT-4 Turbo | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 67.8 | 30.5 |
| Released | 2026-07-24 | 2023-11-06 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $5 | $10 |
| Output $ / M tokens | $25 | $30 |
| Results tracked | 57 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), GPT-4 Turbo: 33.8 (#249)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| WeirdML | 91.8% | 18% |
| LMArena Coding | 1534 | 1268 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
| SciCode | 56.4% | — |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 58.2% |
| ALE-Bench | 2,165 | — |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
Claude Opus 5: 55.6 (#1), GPT-4 Turbo: —
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| APEX-Agents | 65.8% | — |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| METR Time Horizons | — | 36.7% |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), GPT-4 Turbo: 15.3 (#317)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| SimpleBench | 80.6% | 25.1% |
| Chess Puzzles | 42% | 6% |
| LMArena Hard Prompts | 1526 | 1251 |
| DTBench | 97.9% | 61.6% |
| LMCA | 64.5% | 9.8% |
| Epoch Capabilities Index | 162.78 | 127.25 |
| ARC-AGI-2 | 90.4% | — |
| NYT Connections (extended) | 94.3% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 29.1% | — |
| EBR-Bench | 45.7% | — |
| Mystery Game Puzzles | 59% | — |
| Bench to the Future 3 | 0.12 | — |
| ForecastBench | — | 59.4 |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), GPT-4 Turbo: 9.0 (#322)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 0.7% |
| OTIS Mock AIME 2024-2025 | 98.9% | 6.7% |
| LMArena Math | 1531 | 1272 |
| FrontierMath Tier 4 | 73.2% | — |
| ProofBench | 99% | — |
| MATH Level 5 | — | 46.7% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), GPT-4 Turbo: 24.3 (#268)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 93.9% | 46.6% |
| LMArena Expert | 1557 | 1223 |
| SimpleQA Verified | 59.9% | — |
| Confabulations | — | 28.4% |
| MMLU | — | 81.3% |
Multimodal Claude Opus 5 leads
Claude Opus 5: 50.8 (#8), GPT-4 Turbo: 30.6 (#110)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | 1319 | 1090 |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), GPT-4 Turbo: 40.5 (#216)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1501 | 1245 |
| LMArena Chinese | 1574 | 1242 |
| LMArena French | 1519 | 1276 |
| LMArena German | 1524 | 1259 |
| LMArena Japanese | 1516 | 1194 |
| LMArena Korean | 1521 | 1187 |
| LMArena Russian | 1507 | 1259 |
| LMArena Spanish | 1519 | 1260 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), GPT-4 Turbo: 65.8 (#216)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1517 | 1249 |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), GPT-4 Turbo: 38.0 (#206)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1515 | 1254 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), GPT-4 Turbo: 47.7 (#206)
| Benchmark | Claude Opus 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1507 | 1272 |
| LMArena Creative Writing | 1491 | 1269 |
| LMArena Multi-Turn | 1499 | 1267 |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |
Frequently asked questions
Is Claude Opus 5 better than GPT-4 Turbo?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 30.5 on the Noometry Index.
Which is cheaper, Claude Opus 5 or GPT-4 Turbo?
Claude Opus 5 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is Claude Opus 5 or GPT-4 Turbo better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 128K.
How many benchmarks do Claude Opus 5 and GPT-4 Turbo share?
27 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and GPT-4 Turbo has 36.