# Claude 3 Haiku vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Inkling in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 88.9% for Inkling.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Inkling |
|---|---|---|
| Provider | Anthropic | Thinking Machines Lab |
| Noometry Index | 25.7 | 44.1 |
| Rank | 333 | 75 |
| Context | — | 66K |
| Input $/M | — | $1.87 |
| Output $/M | — | $4.68 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Inkling: 34.1 (#229)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| WeirdML | 9.8% | 32.3% |
| LMArena Coding | 1199 | 1463 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1412 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 946 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Inkling: 29.5 (#76)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Inkling: 40.6 (#48)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1452 |
| DTBench | 50.1% | 87.5% |
| LMCA | 8.8% | 37.6% |
| Epoch Capabilities Index | 118.3 | 148.6 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 34.2% | — |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Inkling: 31.2 (#198)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 88.9% |
| LMArena Math | 1188 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| ProofBench | — | 0% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Inkling: 55.2 (#44)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| GPQA Diamond | 36.3% | 88.3% |
| LMArena Expert | 1148 | 1468 |
| SimpleQA Verified | — | 40.3% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Inkling: —

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Inkling: 54.2 (#49)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| LMArena Non-English | 1178 | 1434 |
| LMArena Chinese | 1155 | 1495 |
| LMArena French | 1194 | 1453 |
| LMArena German | 1174 | 1456 |
| LMArena Japanese | 1102 | 1428 |
| LMArena Korean | 1108 | 1401 |
| LMArena Russian | 1204 | 1430 |
| LMArena Spanish | 1165 | 1442 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Inkling: 75.3 (#65)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| LMArena Instruction Following | 1174 | 1427 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Inkling: 43.9 (#79)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| LMArena Longer Query | 1191 | 1436 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Inkling: 65.5 (#48)

| Benchmark | Claude 3 Haiku | Inkling |
|---|---|---|
| LMArena Text | 1195 | 1443 |
| LMArena Creative Writing | 1157 | 1390 |
| EQ-Bench Creative Writing | 717 | 1611 |
| LMArena Multi-Turn | 1190 | 1436 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is Claude 3 Haiku better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Inkling better for coding?

Inkling scores higher on coding benchmarks: 34.1 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Inkling share?

24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Inkling has 41.