Model comparison
Inkling-Small vs Ministral 8B
Inkling-Small is the stronger model overall, scoring 46.5 to 27.8 on the Noometry Index. Ministral 8B costs 6.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Mistral AISummary
- They share 13 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Ministral 8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.3 to 12.5.
- The biggest single-benchmark swing is GPQA Diamond: 88.5% for Inkling-Small and 27.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 128K.
Side by side
| Inkling-Small | Ministral 8B | |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 46.5 | 27.8 |
| Released | 2026-07-15 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 524K | 128K |
| Max output | 1.05M | 128K |
| Input $ / M tokens | $0.45 | $0.10 |
| Output $ / M tokens | $1.20 | $0.10 |
| Results tracked | 33 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.3 (#80), Ministral 8B: 34.4 (#226)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Coding | 1451 | 1202 |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
Agentic & Tool Use Not comparable
Inkling-Small: —, Ministral 8B: 16.2 (#140)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Inkling-Small leads
Inkling-Small: 39.0 (#53), Ministral 8B: 17.7 (#279)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1191 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 45.7% |
| Epoch Capabilities Index | 150.13 | — |
Math Inkling-Small leads
Inkling-Small: 44.9 (#65), Ministral 8B: 23.7 (#262)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Math | 1453 | 1188 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
| MATH Level 5 | — | 14.9% |
Knowledge Inkling-Small leads
Inkling-Small: 48.3 (#71), Ministral 8B: 12.5 (#292)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| GPQA Diamond | 88.5% | 27.1% |
| LMArena Expert | 1442 | 1170 |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Not comparable
Inkling-Small: 38.4 (#59), Ministral 8B: —
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#102), Ministral 8B: 35.3 (#242)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1400 | 1165 |
| LMArena Chinese | 1458 | 1193 |
| LMArena Russian | 1392 | 1195 |
| LMArena French | 1438 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1355 | — |
| LMArena Spanish | 1426 | — |
Instruction Following Inkling-Small leads
Inkling-Small: 73.9 (#112), Ministral 8B: 60.7 (#245)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1161 |
Long Context Inkling-Small leads
Inkling-Small: 42.7 (#113), Ministral 8B: 36.7 (#222)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1401 | 1212 |
Writing & Preference Inkling-Small leads
Inkling-Small: 59.8 (#102), Ministral 8B: 39.8 (#241)
| Benchmark | Inkling-Small | Ministral 8B |
|---|---|---|
| LMArena Text | 1413 | 1191 |
| LMArena Creative Writing | 1330 | 1175 |
| LMArena Multi-Turn | 1420 | 1166 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Ministral 8B?
Inkling-Small is the stronger model overall, scoring 46.5 to 27.8 on the Noometry Index. Ministral 8B costs 6.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Inkling-Small or Ministral 8B better for coding?
Inkling-Small scores higher on coding benchmarks: 43.3 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 128K.
How many benchmarks do Inkling-Small and Ministral 8B share?
13 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Ministral 8B has 17.