# Inkling vs Mixtral 8x22B

> Inkling is the stronger model overall, scoring 44.1 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-vs-mixtral-8x22b
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Inkling scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 15.1.
- The biggest single-benchmark swing is GPQA Diamond: 88.3% for Inkling and 34.1% for Mixtral 8x22B.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Inkling accepts more context: 66K tokens versus 64K.

## Snapshot

| | Inkling | Mixtral 8x22B |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 27.1 |
| Rank | 80 | 333 |
| Context | 66K | 64K |
| Input $/M | $1.87 | $2 |
| Output $/M | $4.68 | $6 |
| Weights | Open | Open |

## Coding

- Inkling: 34.5 (#234)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| WeirdML | 32.3% | 3.2% |
| LMArena Coding | 1464 | 1166 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 946 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| Cybench | — | 7.5% |

## Reasoning

- Inkling: 40.4 (#56)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1150 |
| DTBench | 87.5% | 55.1% |
| Epoch Capabilities Index | 148.54 | 122.03 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LMCA | 37.6% | — |
| ForecastBench | — | 56.3 |

## Math

- Inkling: 31.3 (#225)
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1479 | 1184 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Inkling: 55.1 (#49)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 88.3% | 34.1% |
| LMArena Expert | 1465 | 1113 |
| SimpleQA Verified | 40.3% | — |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- Inkling: 54.0 (#52)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1434 | 1128 |
| LMArena Chinese | 1490 | 1116 |
| LMArena French | 1458 | 1166 |
| LMArena German | 1446 | 1141 |
| LMArena Japanese | 1429 | 1037 |
| LMArena Korean | 1404 | 1057 |
| LMArena Russian | 1429 | 1158 |
| LMArena Spanish | 1448 | 1151 |

## Instruction Following

- Inkling: 75.1 (#71)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- Inkling: 43.8 (#86)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1434 | 1144 |

## Writing & Preference

- Inkling: 65.2 (#51)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | Inkling | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1441 | 1162 |
| LMArena Creative Writing | 1387 | 1141 |
| LMArena Multi-Turn | 1436 | 1130 |
| EQ-Bench Creative Writing | 1611 | — |
| WildBench | — | 71.1% |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than Mixtral 8x22B?

Inkling is the stronger model overall, scoring 44.1 to 27.1 on the Noometry Index.

### Which is cheaper, Inkling or Mixtral 8x22B?

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is Inkling or Mixtral 8x22B better for coding?

Inkling scores higher on coding benchmarks: 34.5 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

Inkling does, with 66K tokens against 64K.

### How many benchmarks do Inkling and Mixtral 8x22B share?

21 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mixtral 8x22B has 34.