Model comparison
Chatgpt 4o Latest 20250326 vs Claude Haiku 4.5
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 39.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 6 categories and Claude Haiku 4.5 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Chatgpt 4o Latest 20250326 leads 33.8 to 15.1.
Side by side
| Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Noometry Index | 43.8 | 39.5 |
| Released | — | 2025-10-15 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 64K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $5 |
| Results tracked | 21 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Chatgpt 4o Latest 20250326: 41.6 (#122), Claude Haiku 4.5: 44.0 (#78)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Coding | 1413 | 1453 |
| SWE-bench Verified (bash only) | — | 66.6% |
| LMArena WebDev | — | 1330 |
| SWE-bench Multilingual | — | 64.7% |
| SciCode | — | 43.3% |
| WeirdML | — | 45.4% |
| ALE-Bench | — | 653.48 |
Agentic & Tool Use Not comparable
Chatgpt 4o Latest 20250326: —, Claude Haiku 4.5: 33.6 (#52)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| Terminal-Bench | — | 35.5% |
| Berkeley Function Calling Leaderboard | — | 68.7% |
| DeepResearch Bench | — | 45.5% |
| BALROG | — | 31.2% |
| ExploitBench | — | 13.7% |
| Vending-Bench 2 | — | 458.89 |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 33.8 (#71), Claude Haiku 4.5: 15.1 (#320)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1420 |
| ARC-AGI-2 | — | 4% |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | — | 14.3% |
| ARC-AGI-1 | — | 47.7% |
| CritPt | — | 0% |
| Chess Puzzles | — | 8% |
| DTBench | — | 73.6% |
| LMCA | — | 30.9% |
| Epoch Capabilities Index | — | 142.41 |
| ForecastBench | — | 61.4 |
Math Claude Haiku 4.5 leads
Chatgpt 4o Latest 20250326: 38.6 (#134), Claude Haiku 4.5: 44.9 (#78)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Math | 1407 | 1396 |
| OTIS Mock AIME 2024-2025 | — | 66.7% |
| Omni-MATH | — | 56.1% |
| MATH Level 5 | — | 96.4% |
| FrontierMath (Feb 2025 set) | — | 5.9% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 39.2 (#137), Claude Haiku 4.5: 37.7 (#153)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Expert | 1401 | 1442 |
| GPQA Diamond | — | 71.2% |
| SimpleQA Verified | — | 13.2% |
| MMLU-Pro | — | 77.7% |
| Confabulations | 16.6% | — |
| Vectara Hallucination Rate | — | 9.8% |
| GPQA (HELM) | — | 60.5% |
Multimodal Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 39.6 (#58), Claude Haiku 4.5: 26.8 (#118)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Vision | 1243 | — |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1420 |
Multilingual Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 52.9 (#76), Claude Haiku 4.5: 49.9 (#129)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Non-English | 1419 | 1377 |
| LMArena Chinese | 1457 | 1417 |
| LMArena French | 1446 | 1408 |
| LMArena German | 1423 | 1375 |
| LMArena Japanese | 1405 | 1339 |
| LMArena Korean | 1396 | 1347 |
| LMArena Russian | 1429 | 1381 |
| LMArena Spanish | 1434 | 1420 |
Instruction Following Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 74.0 (#107), Claude Haiku 4.5: 71.4 (#149)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1414 |
| IFEval | — | 80.1% |
Long Context Too close to call
Chatgpt 4o Latest 20250326: 43.1 (#107), Claude Haiku 4.5: 43.6 (#92)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Longer Query | 1413 | 1427 |
Writing & Preference Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 62.6 (#72), Claude Haiku 4.5: 57.9 (#123)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude Haiku 4.5 |
|---|---|---|
| LMArena Text | 1429 | 1396 |
| LMArena Creative Writing | 1405 | 1372 |
| LMArena Multi-Turn | 1454 | 1409 |
| EQ-Bench Creative Writing | 1501 | — |
| WildBench | — | 83.9% |
| EQ-Bench 4 | — | 1064 |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than Claude Haiku 4.5?
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.8 to 39.5 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or Claude Haiku 4.5 better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 41.6 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and Claude Haiku 4.5 share?
17 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Claude Haiku 4.5 has 53.