Model comparison
Inkling vs Mixtral 8x7B
Inkling is the stronger model overall, scoring 44.1 to 27.1 on the Noometry Index. Mixtral 8x7B costs 3.7× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Inkling scores higher in 8 categories and Mixtral 8x7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 11.0.
- The biggest single-benchmark swing is GPQA Diamond: 88.3% for Inkling and 30.6% for Mixtral 8x7B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Inkling accepts more context: 66K tokens versus 32K.
Side by side
| Inkling | Mixtral 8x7B | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 27.1 |
| Released | 2026-07-15 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 66K | 32K |
| Max output | 66K | 32K |
| Input $ / M tokens | $1.87 | $0.70 |
| Output $ / M tokens | $4.68 | $0.70 |
| Results tracked | 41 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Inkling: 34.5 (#234), Mixtral 8x7B: 32.8 (#269)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1464 | 1126 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Mixtral 8x7B: —
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1115 |
| DTBench | 87.5% | 49.6% |
| Epoch Capabilities Index | 148.54 | 118.47 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LMCA | 37.6% | — |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Inkling leads
Inkling: 31.3 (#225), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1479 | 1147 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge Inkling leads
Inkling: 55.1 (#49), Mixtral 8x7B: 11.0 (#301)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 88.3% | 30.6% |
| LMArena Expert | 1465 | 1088 |
| SimpleQA Verified | 40.3% | — |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual Inkling leads
Inkling: 54.0 (#52), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1434 | 1077 |
| LMArena Chinese | 1490 | 1055 |
| LMArena French | 1458 | 1166 |
| LMArena German | 1446 | 1114 |
| LMArena Japanese | 1429 | 931 |
| LMArena Korean | 1404 | 968 |
| LMArena Russian | 1429 | 1090 |
| LMArena Spanish | 1448 | 1111 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1109 |
| IFEval | — | 57.5% |
Long Context Inkling leads
Inkling: 43.8 (#86), Mixtral 8x7B: 33.4 (#260)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1434 | 1103 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Inkling | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1441 | 1132 |
| LMArena Creative Writing | 1387 | 1109 |
| LMArena Multi-Turn | 1436 | 1115 |
| EQ-Bench Creative Writing | 1611 | — |
| WildBench | — | 67.3% |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Mixtral 8x7B?
Inkling is the stronger model overall, scoring 44.1 to 27.1 on the Noometry Index. Mixtral 8x7B costs 3.7× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Mixtral 8x7B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Mixtral 8x7B better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Inkling does, with 66K tokens against 32K.
How many benchmarks do Inkling and Mixtral 8x7B share?
20 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mixtral 8x7B has 38.