Model comparison
Claude 3.5 Haiku vs GPT-5.3 Codex
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 29.2 on the Noometry Index.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and GPT-5.3 Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 28.0.
- The biggest single-benchmark swing is WeirdML: 30.7% for Claude 3.5 Haiku and 79.3% for GPT-5.3 Codex.
Side by side
| Claude 3.5 Haiku | GPT-5.3 Codex | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.2 | 45.8 |
| Released | 2024-10-22 | 2026-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 49 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
Claude 3.5 Haiku: 32.9 (#265), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| WeirdML | 30.7% | 79.3% |
| SWE-bench Verified | — | 74.8% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1409 |
| SciCode | 27.4% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| LMArena Coding | 1286 | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 1,655 |
Agentic & Tool Use GPT-5.3 Codex leads
Claude 3.5 Haiku: 28.0 (#95), GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | — | 78.4% |
| BALROG | 19.3% | — |
| METR Time Horizons | — | 74.5% |
| Vending-Bench 2 | — | 5,940 |
Reasoning Not comparable
Claude 3.5 Haiku: 17.7 (#290), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 127.15 | 156.77 |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| LiveBench | 43.5% | — |
Math Not comparable
Claude 3.5 Haiku: 14.7 (#300), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| LMArena Math | 1244 | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Not comparable
Claude 3.5 Haiku: 18.7 (#281), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| LMArena Expert | 1208 | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Not comparable
Claude 3.5 Haiku: 40.0 (#218), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1238 | — |
| LMArena Chinese | 1229 | — |
| LMArena French | 1264 | — |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
| LMArena Russian | 1253 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Not comparable
Claude 3.5 Haiku: 62.9 (#234), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
| LMArena Instruction Following | 1241 | — |
Long Context Not comparable
Claude 3.5 Haiku: 38.3 (#200), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1261 | — |
Writing & Preference Not comparable
Claude 3.5 Haiku: 42.7 (#234), GPT-5.3 Codex: —
| Benchmark | Claude 3.5 Haiku | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1233 | — |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LMArena Multi-Turn | 1265 | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than GPT-5.3 Codex?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or GPT-5.3 Codex better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and GPT-5.3 Codex share?
2 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and GPT-5.3 Codex has 8.