# Claude Sonnet 5 vs Tulu 3 (Tülu 3) 70B

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-tulu-3-70b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 14.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 4.4% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Provider | Anthropic | Allen Institute for AI (Ai2) |
| Noometry Index | 54.6 | 33.0 |
| Rank | 29 | 251 |
| Context | 1M | — |
| Input $/M | $2 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- Tulu 3 (Tülu 3) 70B: 36.0 (#214)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1483 | 1235 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| ALE-Bench | 1,463 | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- Tulu 3 (Tülu 3) 70B: —

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- Tulu 3 (Tülu 3) 70B: 23.9 (#169)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1220 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 156.21 | — |
| ForecastBench | 61.1 | — |

## Math

- Claude Sonnet 5: 66.2 (#27)
- Tulu 3 (Tülu 3) 70B: 14.2 (#303)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 4.4% |
| LMArena Math | 1467 | 1242 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| MATH Level 5 | — | 42.7% |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- Tulu 3 (Tülu 3) 70B: 25.0 (#264)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 90.5% | 46.3% |
| SimpleQA Verified | 33.7% | — |
| LMArena Expert | 1490 | — |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- Tulu 3 (Tülu 3) 70B: —

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- Tulu 3 (Tülu 3) 70B: 39.9 (#222)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1431 | 1236 |
| LMArena Chinese | 1477 | 1249 |
| LMArena Russian | 1451 | 1246 |
| LMArena French | 1460 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Spanish | 1437 | — |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- Tulu 3 (Tülu 3) 70B: 64.8 (#227)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1452 | 1233 |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- Tulu 3 (Tülu 3) 70B: 37.1 (#222)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1463 | 1224 |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- Tulu 3 (Tülu 3) 70B: 45.6 (#223)

| Benchmark | Claude Sonnet 5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1442 | 1256 |
| LMArena Creative Writing | 1416 | 1231 |
| LMArena Multi-Turn | 1454 | 1252 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than Tulu 3 (Tülu 3) 70B?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 33.0 on the Noometry Index.

### Is Claude Sonnet 5 or Tulu 3 (Tülu 3) 70B better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 36.0 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 5 and Tulu 3 (Tülu 3) 70B share?

13 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.