Model comparison
Claude 3.5 Haiku vs GPT-6.1 Sol
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 29.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and GPT-6.1 Sol in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 100% for GPT-6.1 Sol.
Side by side
| Claude 3.5 Haiku | GPT-6.1 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.2 | 65.6 |
| Released | 2024-10-22 | 2026-09-29 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 49 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
Claude 3.5 Haiku: 32.9 (#265), GPT-6.1 Sol: 63.2 (#8)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| SciCode | 27.4% | 55.8% |
| LMArena Coding | 1286 | 1487 |
| DeepSWE | — | 75.2% |
| FrontierCode | — | 50.2% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1755 |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use GPT-6.1 Sol leads
Claude 3.5 Haiku: 28.0 (#95), GPT-6.1 Sol: 39.6 (#26)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| APEX-Agents | — | 60% |
| BALROG | 19.3% | — |
| GDP.pdf | — | 32% |
Reasoning GPT-6.1 Sol leads
Claude 3.5 Haiku: 17.7 (#290), GPT-6.1 Sol: 81.9 (#2)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| CritPt | 0% | 31.7% |
| LMArena Hard Prompts | 1251 | 1466 |
| Epoch Capabilities Index | 127.15 | 166.09 |
| ARC-AGI-2 | — | 94.2% |
| NYT Connections (extended) | — | 95.5% |
| ARC-AGI-1 | — | 98.5% |
| Chess Puzzles | — | 61% |
| EBR-Bench | — | 54.3% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 80% |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| LiveBench | 43.5% | — |
Math GPT-6.1 Sol leads
Claude 3.5 Haiku: 14.7 (#300), GPT-6.1 Sol: 93.7 (#1)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 100% |
| LMArena Math | 1244 | 1464 |
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 100% |
| ProofBench | — | 99% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge GPT-6.1 Sol leads
Claude 3.5 Haiku: 18.7 (#281), GPT-6.1 Sol: 71.8 (#4)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| GPQA Diamond | 38.1% | 95.4% |
| LMArena Expert | 1208 | 1502 |
| SimpleQA Verified | — | 73.9% |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal GPT-6.1 Sol leads
Claude 3.5 Haiku: 26.8 (#117), GPT-6.1 Sol: 52.7 (#5)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| LMArena Vision | 1092 | 1288 |
| GeoBench | 34% | — |
| Furniture Assembly | — | 80% |
Multilingual GPT-6.1 Sol leads
Claude 3.5 Haiku: 40.0 (#218), GPT-6.1 Sol: 54.3 (#46)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| LMArena Non-English | 1238 | 1438 |
| LMArena Chinese | 1229 | 1477 |
| LMArena Russian | 1253 | 1455 |
| LMArena French | 1264 | — |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
| LMArena Spanish | 1261 | — |
Instruction Following GPT-6.1 Sol leads
Claude 3.5 Haiku: 62.9 (#234), GPT-6.1 Sol: 77.0 (#29)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| LMArena Instruction Following | 1241 | 1468 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context GPT-6.1 Sol leads
Claude 3.5 Haiku: 38.3 (#200), GPT-6.1 Sol: 44.9 (#54)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| LMArena Longer Query | 1261 | 1465 |
Writing & Preference GPT-6.1 Sol leads
Claude 3.5 Haiku: 42.7 (#234), GPT-6.1 Sol: 63.6 (#63)
| Benchmark | Claude 3.5 Haiku | GPT-6.1 Sol |
|---|---|---|
| LMArena Text | 1255 | 1447 |
| LMArena Creative Writing | 1233 | 1432 |
| LMArena Multi-Turn | 1265 | 1449 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than GPT-6.1 Sol?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or GPT-6.1 Sol better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and GPT-6.1 Sol share?
18 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and GPT-6.1 Sol has 34.