Model comparison
Chatgpt 4o Latest 20250326 vs Claude Opus 5
Claude Opus 5 is the stronger model overall, scoring 67.7 to 43.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 0 categories and Claude Opus 5 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.1 to 35.8.
Side by side
| Chatgpt 4o Latest 20250326 | Claude Opus 5 | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Noometry Index | 43.2 | 67.7 |
| Released | — | 2026-07-24 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $5 |
| Output $ / M tokens | — | $25 |
| Results tracked | 21 | 57 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 41.0 (#122), Claude Opus 5: 67.0 (#5)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Coding | 1413 | 1533 |
| DeepSWE | — | 73.6% |
| FrontierCode | — | 53.4% |
| CursorBench | — | 46.6% |
| LMArena WebDev | — | 1694 |
| FrontierSWE | — | 52% |
| SciCode | — | 56.4% |
| WeirdML | — | 91.8% |
| ALE-Bench | — | 2,165 |
Agentic & Tool Use Not comparable
Chatgpt 4o Latest 20250326: —, Claude Opus 5: 55.5 (#1)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| 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% |
| Vending-Bench 2 | — | 11,182 |
Reasoning Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 32.8 (#64), Claude Opus 5: 77.1 (#3)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1525 |
| ARC-AGI-2 | — | 90.4% |
| SimpleBench | — | 80.6% |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | — | 94.3% |
| ARC-AGI-1 | — | 97.5% |
| CritPt | — | 29.1% |
| Chess Puzzles | — | 42% |
| EBR-Bench | — | 45.7% |
| Mystery Game Puzzles | — | 59% |
| DTBench | — | 97.9% |
| LMCA | — | 64.5% |
| Bench to the Future 3 | — | 0.12 |
| Epoch Capabilities Index | — | 162.67 |
Math Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 35.8 (#134), Claude Opus 5: 86.1 (#6)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Math | 1407 | 1533 |
| FrontierMath (Tiers 1-3) | — | 85.6% |
| FrontierMath Tier 4 | — | 73.2% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 99% |
Knowledge Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 38.7 (#131), Claude Opus 5: 66.8 (#8)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Expert | 1400 | 1558 |
| GPQA Diamond | — | 93.9% |
| SimpleQA Verified | — | 59.9% |
| Confabulations | 16.6% | — |
Multimodal Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 38.9 (#54), Claude Opus 5: 51.1 (#6)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Vision | 1243 | 1321 |
| Blueprint-Bench 2 | — | 30.4% |
| Furniture Assembly | — | 60.8% |
| LMArena Document | — | 1516 |
Multilingual Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 53.1 (#72), Claude Opus 5: 58.8 (#3)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Non-English | 1419 | 1500 |
| LMArena Chinese | 1456 | 1575 |
| LMArena French | 1447 | 1522 |
| LMArena German | 1424 | 1522 |
| LMArena Japanese | 1406 | 1510 |
| LMArena Korean | 1397 | 1526 |
| LMArena Russian | 1429 | 1507 |
| LMArena Spanish | 1435 | 1519 |
Instruction Following Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 74.2 (#102), Claude Opus 5: 79.3 (#5)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1516 |
Long Context Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 43.1 (#104), Claude Opus 5: 46.5 (#20)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Longer Query | 1413 | 1516 |
Writing & Preference Claude Opus 5 leads
Chatgpt 4o Latest 20250326: 62.8 (#68), Claude Opus 5: 79.3 (#2)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Opus 5 |
|---|---|---|
| LMArena Text | 1429 | 1506 |
| LMArena Creative Writing | 1406 | 1491 |
| EQ-Bench Creative Writing | 1501 | 2133 |
| LMArena Multi-Turn | 1454 | 1496 |
| EQ-Bench 4 | — | 1385 |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than Claude Opus 5?
Claude Opus 5 is the stronger model overall, scoring 67.7 to 43.2 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or Claude Opus 5 better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 41.0 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and Claude Opus 5 share?
19 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Claude Opus 5 has 57.