Model comparison
Claude Haiku 5.5 vs GPT-4
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 29.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 4 categories and GPT-4 in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Claude Haiku 5.5 and 1.1% for GPT-4.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $30 / $60 for GPT-4.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 8K.
Side by side
| Claude Haiku 5.5 | GPT-4 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 49.5 | 29.1 |
| Released | 2026-10-07 | 2023-03-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 8K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.10 | $30 |
| Output $ / M tokens | $0.50 | $60 |
| Results tracked | 9 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 5.5 leads
Claude Haiku 5.5: 49.2 (#50), GPT-4: 31.6 (#283)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| LMArena WebDev | 1587 | — |
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| LMArena Coding | — | 1254 |
| BigCodeBench Complete | — | 57.2% |
| HumanEval+ | — | 79.3% |
Agentic & Tool Use Not comparable
Claude Haiku 5.5: —, GPT-4: —
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |
Reasoning Claude Haiku 5.5 leads
Claude Haiku 5.5: 35.2 (#69), GPT-4: 17.8 (#289)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| Mystery Game Puzzles | 30% | 12% |
| NYT Connections (extended) | 65.7% | — |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | — | 1241 |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| Epoch Capabilities Index | — | 125.89 |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |
Math Claude Haiku 5.5 leads
Claude Haiku 5.5: 73.6 (#18), GPT-4: 10.8 (#309)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 1.1% |
| FrontierMath (Tiers 1-3) | 75.1% | — |
| FrontierMath Tier 4 | 46.3% | — |
| LMArena Math | — | 1269 |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |
Knowledge Claude Haiku 5.5 leads
Claude Haiku 5.5: 50.8 (#70), GPT-4: 18.4 (#282)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| GPQA Diamond | 89.6% | 35.7% |
| SimpleQA Verified | 23.8% | — |
| LMArena Expert | — | 1211 |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |
Multimodal Not comparable
Claude Haiku 5.5: 43.7 (#21), GPT-4: —
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| Furniture Assembly | 47.5% | — |
Multilingual Not comparable
Claude Haiku 5.5: —, GPT-4: 40.6 (#215)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| LMArena Non-English | — | 1246 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1283 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1184 |
| LMArena Russian | — | 1251 |
| LMArena Spanish | — | 1261 |
Instruction Following Not comparable
Claude Haiku 5.5: —, GPT-4: 65.3 (#222)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| LMArena Instruction Following | — | 1241 |
Long Context Not comparable
Claude Haiku 5.5: —, GPT-4: 37.7 (#212)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| LMArena Longer Query | — | 1244 |
Writing & Preference Not comparable
Claude Haiku 5.5: —, GPT-4: 34.9 (#268)
| Benchmark | Claude Haiku 5.5 | GPT-4 |
|---|---|---|
| LMArena Text | — | 1263 |
| LMArena Creative Writing | — | 1244 |
| EQ-Bench Creative Writing | — | 752 |
| LMArena Multi-Turn | — | 1257 |
Frequently asked questions
Is Claude Haiku 5.5 better than GPT-4?
Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 29.1 on the Noometry Index.
Which is cheaper, Claude Haiku 5.5 or GPT-4?
Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GPT-4 lists at $30 and $60.
Is Claude Haiku 5.5 or GPT-4 better for coding?
Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 5.5 does, with 1M tokens against 8K.
How many benchmarks do Claude Haiku 5.5 and GPT-4 share?
3 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and GPT-4 has 38.