Model comparison
Claude 3.5 Haiku vs Claude Opus 4.6
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 29.2 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Claude Opus 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.6 leads 63.0 to 14.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 94.4% for Claude Opus 4.6.
Side by side
| Claude 3.5 Haiku | Claude Opus 4.6 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 29.2 | 58.2 |
| Released | 2024-10-22 | 2026-02-04 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 128K |
| Input $ / M tokens | — | $5 |
| Output $ / M tokens | — | $25 |
| Results tracked | 49 | 68 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.6 leads
Claude 3.5 Haiku: 32.9 (#265), Claude Opus 4.6: 57.2 (#20)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| WeirdML | 30.7% | 78% |
| LMArena Coding | 1286 | 1536 |
| SWE-bench Verified | — | 78.7% |
| FrontierCode | — | 26.6% |
| SWE-bench Verified (bash only) | — | 75.6% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1547 |
| SWE-bench Multilingual | — | 72% |
| SciCode | 27.4% | — |
| GSO | — | 41.2% |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 996.5 |
| AlgoTune | — | 1.47 |
Agentic & Tool Use Claude Opus 4.6 leads
Claude 3.5 Haiku: 28.0 (#95), Claude Opus 4.6: 51.1 (#4)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| Terminal-Bench | — | 79.8% |
| APEX-Agents | — | 46.3% |
| Remote Labor Index | — | 4.2% |
| τ²-bench Banking | — | 27.3% |
| Cybench | — | 93% |
| DeepResearch Bench | — | 55.3% |
| BALROG | 19.3% | — |
| GBAEval | — | 44.1% |
| LMArena Search | — | 1253 |
| METR Time Horizons | — | 78.9% |
| Vending-Bench 2 | — | 8,018 |
Reasoning Claude Opus 4.6 leads
Claude 3.5 Haiku: 17.7 (#290), Claude Opus 4.6: 57.8 (#23)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1527 |
| DTBench | 56.7% | 91.2% |
| Epoch Capabilities Index | 127.15 | 155.24 |
| ARC-AGI-2 | — | 69.2% |
| SimpleBench | — | 67.6% |
| Kagi LLM Benchmark | — | 83.6% |
| NYT Connections (extended) | — | 92.1% |
| ARC-AGI-1 | — | 94% |
| CritPt | 0% | — |
| Chess Puzzles | — | 17% |
| EnigmaEval | — | 7.6% |
| Thematic Generalization | — | 80.6% |
| EBR-Bench | — | 12.7% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 25% |
| LiveBench Data Analysis | 48.5% | — |
| LMCA | — | 55.8% |
| ForecastBench | — | 60 |
| LiveBench | 43.5% | — |
Math Claude Opus 4.6 leads
Claude 3.5 Haiku: 14.7 (#300), Claude Opus 4.6: 63.0 (#31)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 94.4% |
| LMArena Math | 1244 | 1519 |
| FrontierMath (Feb 2025 set) | 0.3% | 40.7% |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 78.5% |
| ProofBench | — | 50% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath Tier 4 (v1) | — | 22.9% |
Knowledge Claude Opus 4.6 leads
Claude 3.5 Haiku: 18.7 (#281), Claude Opus 4.6: 61.9 (#26)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| GPQA Diamond | 38.1% | 90.5% |
| LMArena Expert | 1208 | 1546 |
| Humanity's Last Exam | — | 34.4% |
| SimpleQA Verified | — | 47% |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| Vectara Hallucination Rate | — | 12.2% |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Claude Opus 4.6 leads
Claude 3.5 Haiku: 26.8 (#117), Claude Opus 4.6: 37.3 (#74)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| LMArena Vision | 1092 | 1316 |
| GeoBench | 34% | — |
| Furniture Assembly | — | 28.3% |
| LMArena Document | — | 1507 |
Multilingual Claude Opus 4.6 leads
Claude 3.5 Haiku: 40.0 (#218), Claude Opus 4.6: 57.9 (#6)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| LMArena Non-English | 1238 | 1489 |
| LMArena Chinese | 1229 | 1551 |
| LMArena French | 1264 | 1513 |
| LMArena German | 1237 | 1502 |
| LMArena Japanese | 1175 | 1484 |
| LMArena Korean | 1173 | 1464 |
| LMArena Russian | 1253 | 1497 |
| LMArena Spanish | 1261 | 1510 |
Instruction Following Claude Opus 4.6 leads
Claude 3.5 Haiku: 62.9 (#234), Claude Opus 4.6: 79.5 (#4)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1523 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Claude Opus 4.6 leads
Claude 3.5 Haiku: 38.3 (#200), Claude Opus 4.6: 48.1 (#13)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| LMArena Longer Query | 1261 | 1520 |
| CL-bench | — | 20.7% |
| CL-bench Life | — | 17% |
Writing & Preference Claude Opus 4.6 leads
Claude 3.5 Haiku: 42.7 (#234), Claude Opus 4.6: 73.5 (#10)
| Benchmark | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| LMArena Text | 1255 | 1503 |
| LMArena Creative Writing | 1233 | 1505 |
| EQ-Bench Creative Writing | 1146 | 1809 |
| LMArena Multi-Turn | 1265 | 1513 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 76% | — |
| EQ-Bench 4 | — | 1223 |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Claude Opus 4.6?
Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Claude Opus 4.6 better for coding?
Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Claude Opus 4.6 share?
25 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Claude Opus 4.6 has 68.