Model comparison
Claude 3.5 Sonnet vs Tulu 3 (Tülu 3) 70B
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 33.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3.5 Sonnet leads 52.9 to 45.6.
- The biggest single-benchmark swing is MATH Level 5: 56.9% for Claude 3.5 Sonnet and 42.7% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Anthropic | Allen Institute for AI (Ai2) |
| Noometry Index | 34.6 | 33.0 |
| Released | 2024-06-20 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1342 | 1235 |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.3 (#67), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Too close to call
Claude 3.5 Sonnet: 23.1 (#183), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1220 |
| SimpleBench | 41.4% | — |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 19.2 (#288), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 4.4% |
| LMArena Math | 1307 | 1242 |
| MATH Level 5 | 56.9% | 42.7% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 28.6 (#245), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 55.3% | 46.3% |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| LMArena Expert | 1265 | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 43.2 (#185), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1283 | 1236 |
| LMArena Chinese | 1272 | 1249 |
| LMArena Russian | 1306 | 1246 |
| LMArena French | 1305 | — |
| LMArena German | 1297 | — |
| LMArena Japanese | 1234 | — |
| LMArena Korean | 1200 | — |
| LMArena Spanish | 1290 | — |
Instruction Following Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 68.8 (#182), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1233 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1311 | 1224 |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Claude 3.5 Sonnet | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1298 | 1256 |
| LMArena Creative Writing | 1292 | 1231 |
| LMArena Multi-Turn | 1326 | 1252 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Tulu 3 (Tülu 3) 70B?
Claude 3.5 Sonnet is the stronger model overall, scoring 34.6 to 33.0 on the Noometry Index.
Is Claude 3.5 Sonnet or Tulu 3 (Tülu 3) 70B better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 36.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.