Model comparison
Chatgpt 4o Latest 20250326 vs Claude 3 Haiku
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.2 to 25.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 9 categories and Claude 3 Haiku in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Chatgpt 4o Latest 20250326 leads 62.8 to 29.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 34.2% for Claude 3 Haiku.
Side by side
| Chatgpt 4o Latest 20250326 | Claude 3 Haiku | |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Noometry Index | 43.2 | 25.7 |
| Released | — | 2024-03-07 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 41.0 (#122), Claude 3 Haiku: 26.1 (#320)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| LMArena Coding | 1413 | 1199 |
| WeirdML | — | 9.8% |
| BigCodeBench Instruct | — | 39.4% |
| BigCodeBench Complete | — | 50.1% |
| CadEval | — | 12% |
| HumanEval+ | — | 68.9% |
| MBPP+ | — | 68.8% |
Reasoning Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 32.8 (#64), Claude 3 Haiku: 15.7 (#303)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| Kagi LLM Benchmark | 75% | 34.2% |
| LMArena Hard Prompts | 1424 | 1174 |
| DTBench | — | 50.1% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 118.3 |
| ForecastBench | — | 53.2 |
| WinoGrande | — | 74.2% |
Math Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 35.8 (#134), Claude 3 Haiku: 9.2 (#313)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| LMArena Math | 1407 | 1188 |
| OTIS Mock AIME 2024-2025 | — | 1.8% |
| MATH Level 5 | — | 14.9% |
Knowledge Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 38.7 (#131), Claude 3 Haiku: 17.3 (#280)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| Confabulations | 16.6% | 34.2% |
| LMArena Expert | 1400 | 1148 |
| GPQA Diamond | — | 36.3% |
| MMLU | — | 73.8% |
Multimodal Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 38.9 (#54), Claude 3 Haiku: 23.1 (#123)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| LMArena Vision | 1243 | 950 |
| ScienceQA | — | 72% |
Multilingual Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 53.1 (#72), Claude 3 Haiku: 36.1 (#238)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| LMArena Non-English | 1419 | 1178 |
| LMArena Chinese | 1456 | 1155 |
| LMArena French | 1447 | 1194 |
| LMArena German | 1424 | 1174 |
| LMArena Japanese | 1406 | 1102 |
| LMArena Korean | 1397 | 1108 |
| LMArena Russian | 1429 | 1204 |
| LMArena Spanish | 1435 | 1165 |
Instruction Following Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 74.2 (#102), Claude 3 Haiku: 61.5 (#242)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| LMArena Instruction Following | 1403 | 1174 |
Long Context Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 43.1 (#104), Claude 3 Haiku: 36.1 (#232)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| LMArena Longer Query | 1413 | 1191 |
Writing & Preference Chatgpt 4o Latest 20250326 leads
Chatgpt 4o Latest 20250326: 62.8 (#68), Claude 3 Haiku: 29.8 (#286)
| Benchmark | Chatgpt 4o Latest 20250326 | Claude 3 Haiku |
|---|---|---|
| LMArena Text | 1429 | 1195 |
| LMArena Creative Writing | 1406 | 1157 |
| EQ-Bench Creative Writing | 1501 | 717 |
| LMArena Multi-Turn | 1454 | 1190 |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than Claude 3 Haiku?
Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.2 to 25.7 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or Claude 3 Haiku better for coding?
Chatgpt 4o Latest 20250326 scores higher on coding benchmarks: 41.0 versus 26.1 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and Claude 3 Haiku share?
21 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Claude 3 Haiku has 37.