Model comparison
Claude 3 Haiku vs GPT-5.3 Chat
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 25.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GPT-5.3 Chat in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.3 Chat leads 63.1 to 29.7.
Side by side
| Claude 3 Haiku | GPT-5.3 Chat | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.9 | 42.8 |
| Released | 2024-03-07 | 2026-03-03 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 16K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Chat leads
Claude 3 Haiku: 26.4 (#325), GPT-5.3 Chat: 41.4 (#124)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Coding | 1199 | 1408 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |
Reasoning GPT-5.3 Chat leads
Claude 3 Haiku: 16.3 (#307), GPT-5.3 Chat: 28.5 (#102)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1399 |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |
Math GPT-5.3 Chat leads
Claude 3 Haiku: 9.8 (#319), GPT-5.3 Chat: 38.2 (#142)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Math | 1188 | 1389 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
Knowledge GPT-5.3 Chat leads
Claude 3 Haiku: 17.3 (#285), GPT-5.3 Chat: 38.8 (#140)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Expert | 1148 | 1397 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |
Multimodal Not comparable
Claude 3 Haiku: 23.6 (#128), GPT-5.3 Chat: —
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual GPT-5.3 Chat leads
Claude 3 Haiku: 36.0 (#243), GPT-5.3 Chat: 50.3 (#124)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Non-English | 1178 | 1382 |
| LMArena Chinese | 1155 | 1432 |
| LMArena French | 1195 | 1397 |
| LMArena German | 1174 | 1384 |
| LMArena Japanese | 1102 | 1352 |
| LMArena Korean | 1109 | 1346 |
| LMArena Russian | 1204 | 1400 |
| LMArena Spanish | 1166 | 1371 |
Instruction Following GPT-5.3 Chat leads
Claude 3 Haiku: 61.3 (#247), GPT-5.3 Chat: 72.8 (#129)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Instruction Following | 1173 | 1378 |
Long Context GPT-5.3 Chat leads
Claude 3 Haiku: 36.1 (#237), GPT-5.3 Chat: 42.6 (#120)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Longer Query | 1190 | 1396 |
Writing & Preference GPT-5.3 Chat leads
Claude 3 Haiku: 29.7 (#291), GPT-5.3 Chat: 63.1 (#68)
| Benchmark | Claude 3 Haiku | GPT-5.3 Chat |
|---|---|---|
| LMArena Text | 1195 | 1389 |
| LMArena Creative Writing | 1157 | 1355 |
| EQ-Bench Creative Writing | 717 | 1690 |
| LMArena Multi-Turn | 1190 | 1412 |
Frequently asked questions
Is Claude 3 Haiku better than GPT-5.3 Chat?
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 25.9 on the Noometry Index.
Is Claude 3 Haiku or GPT-5.3 Chat better for coding?
GPT-5.3 Chat scores higher on coding benchmarks: 41.4 versus 26.4 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and GPT-5.3 Chat share?
18 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GPT-5.3 Chat has 18.