# Inkling-Small vs Tulu 3 (Tülu 3) 70B

> Inkling-Small is the stronger model overall, scoring 46.5 to 32.6 on the Noometry Index.

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

## Summary

- They share 13 benchmarks with published results for both. Inkling-Small 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 Inkling-Small leads 44.9 to 13.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 4.4% for Tulu 3 (Tülu 3) 70B.

## Snapshot

| | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Provider | Thinking Machines Lab | Allen Institute for AI (Ai2) |
| Noometry Index | 46.5 | 32.6 |
| Rank | 57 | 242 |
| Context | 524K | — |
| Input $/M | $0.45 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.3 (#80)
- Tulu 3 (Tülu 3) 70B: 35.4 (#211)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1451 | 1236 |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |

## Reasoning

- Inkling-Small: 39.0 (#53)
- Tulu 3 (Tülu 3) 70B: 22.9 (#172)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1220 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.13 | — |

## Math

- Inkling-Small: 44.9 (#65)
- Tulu 3 (Tülu 3) 70B: 13.3 (#297)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 4.4% |
| LMArena Math | 1453 | 1242 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| MATH Level 5 | — | 42.7% |

## Knowledge

- Inkling-Small: 48.3 (#71)
- Tulu 3 (Tülu 3) 70B: 25.1 (#257)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 88.5% | 46.3% |
| SimpleQA Verified | 19.1% | — |
| LMArena Expert | 1442 | — |

## Multimodal

- Inkling-Small: 38.4 (#59)
- Tulu 3 (Tülu 3) 70B: —

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#102)
- Tulu 3 (Tülu 3) 70B: 40.1 (#217)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1400 | 1236 |
| LMArena Chinese | 1458 | 1249 |
| LMArena Russian | 1392 | 1246 |
| LMArena French | 1438 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1355 | — |
| LMArena Spanish | 1426 | — |

## Instruction Following

- Inkling-Small: 73.9 (#112)
- Tulu 3 (Tülu 3) 70B: 65.0 (#222)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1233 |

## Long Context

- Inkling-Small: 42.7 (#113)
- Tulu 3 (Tülu 3) 70B: 37.1 (#217)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1401 | 1224 |

## Writing & Preference

- Inkling-Small: 59.8 (#102)
- Tulu 3 (Tülu 3) 70B: 45.8 (#218)

| Benchmark | Inkling-Small | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1413 | 1256 |
| LMArena Creative Writing | 1330 | 1231 |
| LMArena Multi-Turn | 1420 | 1252 |
| EQ-Bench Creative Writing | 1491 | — |

## FAQ

### Is Inkling-Small better than Tulu 3 (Tülu 3) 70B?

Inkling-Small is the stronger model overall, scoring 46.5 to 32.6 on the Noometry Index.

### Is Inkling-Small or Tulu 3 (Tülu 3) 70B better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 35.4 in the Noometry coding category.

### How many benchmarks do Inkling-Small and Tulu 3 (Tülu 3) 70B share?

13 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.