Model comparison
Chatgpt 4o Latest 20250326 vs Claude Sonnet 4.5
Chatgpt 4o Latest 20250326 and Claude Sonnet 4.5 score almost the same on the Noometry Index (43.8 vs 44.1), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 3 categories and Claude Sonnet 4.5 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 39.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 57.9% for Claude Sonnet 4.5.
Side by side
| Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Noometry Index | 43.8 | 44.1 |
| Released | — | 2025-09-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 64K |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 21 | 73 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.5 leads
Chatgpt 4o Latest 20250326: 41.6 (#122), Claude Sonnet 4.5: 47.3 (#61)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Coding | 1413 | 1489 |
| SWE-bench Verified | — | 71.3% |
| SWE-bench Verified (bash only) | — | 71.4% |
| LMArena WebDev | — | 1393 |
| SWE-bench Multilingual | — | 67% |
| SciCode | — | 44.7% |
| GSO | — | 14.7% |
| WeirdML | — | 47.7% |
| ALE-Bench | — | 796.15 |
| AlgoTune | — | 1.52 |
Agentic & Tool Use Not comparable
Chatgpt 4o Latest 20250326: —, Claude Sonnet 4.5: 38.3 (#32)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| Terminal-Bench | — | 46.5% |
| Berkeley Function Calling Leaderboard | — | 73.2% |
| GDPval | — | 42.5% |
| Remote Labor Index | — | 2.1% |
| τ²-bench Airline | — | 72% |
| τ²-bench Banking | — | 25.3% |
| τ²-bench Retail | — | 72.4% |
| τ²-bench Telecom | — | 84.9% |
| Cybench | — | 60% |
| DeepResearch Bench | — | 52.6% |
| OSWorld | — | 62.9% |
| LMArena Search | — | 1159 |
| METR Time Horizons | — | 67.4% |
| Vending-Bench 2 | — | 3,839 |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 33.8 (#71), Claude Sonnet 4.5: 26.9 (#125)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 57.9% |
| LMArena Hard Prompts | 1424 | 1462 |
| ARC-AGI-2 | — | 13.6% |
| SimpleBench | — | 54.3% |
| NYT Connections (extended) | — | 37.3% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 6% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 83.2% |
| LMCA | — | 38.8% |
| Epoch Capabilities Index | — | 146.84 |
| ForecastBench | — | 61.9 |
Math Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 38.6 (#134), Claude Sonnet 4.5: 32.3 (#216)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Math | 1407 | 1449 |
| FrontierMath (Tiers 1-3) | — | 23.9% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 77.8% |
| ProofBench | — | 19% |
| Omni-MATH | — | 55.3% |
| MATH Level 5 | — | 97.7% |
| FrontierMath (Feb 2025 set) | — | 15.2% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Sonnet 4.5 leads
Chatgpt 4o Latest 20250326: 39.2 (#137), Claude Sonnet 4.5: 48.4 (#76)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Expert | 1401 | 1482 |
| GPQA Diamond | — | 82.3% |
| Humanity's Last Exam | — | 13.7% |
| SimpleQA Verified | — | 30.7% |
| MMLU-Pro | — | 86.9% |
| Confabulations | 16.6% | — |
| Vectara Hallucination Rate | — | 12% |
| GPQA (HELM) | — | 68.6% |
Multimodal Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 39.6 (#58), Claude Sonnet 4.5: 34.8 (#89)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Vision | 1243 | — |
| VPCT | — | 39.8% |
| LMArena Document | — | 1450 |
Multilingual Too close to call
Chatgpt 4o Latest 20250326: 52.9 (#76), Claude Sonnet 4.5: 53.4 (#69)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Non-English | 1419 | 1425 |
| LMArena Chinese | 1457 | 1459 |
| LMArena French | 1446 | 1458 |
| LMArena German | 1423 | 1427 |
| LMArena Japanese | 1405 | 1390 |
| LMArena Korean | 1396 | 1403 |
| LMArena Russian | 1429 | 1437 |
| LMArena Spanish | 1434 | 1457 |
Instruction Following Too close to call
Chatgpt 4o Latest 20250326: 74.0 (#107), Claude Sonnet 4.5: 75.0 (#78)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1459 |
| IFEval | — | 85% |
Long Context Claude Sonnet 4.5 leads
Chatgpt 4o Latest 20250326: 43.1 (#107), Claude Sonnet 4.5: 45.2 (#46)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Longer Query | 1413 | 1476 |
Writing & Preference Claude Sonnet 4.5 leads
Chatgpt 4o Latest 20250326: 62.6 (#72), Claude Sonnet 4.5: 66.5 (#34)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Sonnet 4.5 |
|---|---|---|
| LMArena Text | 1429 | 1439 |
| LMArena Creative Writing | 1405 | 1442 |
| EQ-Bench Creative Writing | 1501 | 1678 |
| LMArena Multi-Turn | 1454 | 1465 |
| WildBench | — | 85.4% |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than Claude Sonnet 4.5?
Chatgpt 4o Latest 20250326 and Claude Sonnet 4.5 score almost the same on the Noometry Index (43.8 vs 44.1), so choose on price, context window or the category you care about most.
Is Chatgpt 4o Latest 20250326 or Claude Sonnet 4.5 better for coding?
Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 41.6 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and Claude Sonnet 4.5 share?
19 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Claude Sonnet 4.5 has 73.