Model comparison
Inkling vs Mistral 7B
Inkling is the stronger model overall, scoring 44.1 to 22.9 on the Noometry Index. Mistral 7B costs 10× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Inkling scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 7.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 0.3% for Mistral 7B.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Inkling accepts more context: 66K tokens versus 8K.
Side by side
| Inkling | Mistral 7B | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 22.9 |
| Released | 2026-07-15 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 66K | 8K |
| Max output | 66K | 8K |
| Input $ / M tokens | $1.87 | $0.25 |
| Output $ / M tokens | $4.68 | $0.25 |
| Results tracked | 41 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Inkling: 34.1 (#229), Mistral 7B: 25.9 (#321)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| LMArena Coding | 1463 | 1082 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 946 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Agentic & Tool Use Not comparable
Inkling: 29.5 (#76), Mistral 7B: —
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.6 (#48), Mistral 7B: 12.6 (#331)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| Chess Puzzles | 21% | 0% |
| LMArena Hard Prompts | 1452 | 1067 |
| DTBench | 87.5% | 42.5% |
| Epoch Capabilities Index | 148.6 | 111.97 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| LMCA | 37.6% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Inkling leads
Inkling: 31.2 (#198), Mistral 7B: 7.6 (#319)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 0.3% |
| LMArena Math | 1482 | 1085 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Inkling leads
Inkling: 55.2 (#44), Mistral 7B: 7.3 (#306)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| GPQA Diamond | 88.3% | 15.2% |
| LMArena Expert | 1468 | 1036 |
| SimpleQA Verified | 40.3% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Inkling leads
Inkling: 54.2 (#49), Mistral 7B: 26.0 (#278)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1434 | 1012 |
| LMArena Chinese | 1495 | 1009 |
| LMArena French | 1453 | 1036 |
| LMArena German | 1456 | 987 |
| LMArena Japanese | 1428 | 878 |
| LMArena Russian | 1430 | 1018 |
| LMArena Spanish | 1442 | 1026 |
| LMArena Korean | 1401 | — |
Instruction Following Inkling leads
Inkling: 75.3 (#65), Mistral 7B: 54.5 (#275)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1427 | 1060 |
Long Context Inkling leads
Inkling: 43.9 (#79), Mistral 7B: 32.2 (#266)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1436 | 1060 |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), Mistral 7B: 30.9 (#281)
| Benchmark | Inkling | Mistral 7B |
|---|---|---|
| LMArena Text | 1443 | 1090 |
| LMArena Creative Writing | 1390 | 1068 |
| LMArena Multi-Turn | 1436 | 1062 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Mistral 7B?
Inkling is the stronger model overall, scoring 44.1 to 22.9 on the Noometry Index. Mistral 7B costs 10× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Mistral 7B better for coding?
Inkling scores higher on coding benchmarks: 34.1 versus 25.9 in the Noometry coding category.
Which has the bigger context window?
Inkling does, with 66K tokens against 8K.
How many benchmarks do Inkling and Mistral 7B share?
21 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mistral 7B has 37.