Model comparison
Kimi K3 vs Ministral 8B
Kimi K3 is the stronger model overall, scoring 59.5 to 28.2 on the Noometry Index. Ministral 8B costs 40× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Mistral AISummary
- They share 14 benchmarks with published results for both. Kimi K3 scores higher in 9 categories and Ministral 8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K3 leads 63.2 to 12.6.
- The biggest single-benchmark swing is GPQA Diamond: 93.1% for Kimi K3 and 27.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 262K.
Side by side
| Kimi K3 | Ministral 8B | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 28.2 |
| Released | 2026-07-16 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 1.05M | 262K |
| Input $ / M tokens | $3 | $0.15 |
| Output $ / M tokens | $15 | $0.15 |
| Results tracked | 53 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Ministral 8B: 35.0 (#230)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1508 | 1202 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Kimi K3 leads
Kimi K3: 41.8 (#20), Ministral 8B: 16.4 (#148)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| APEX-Agents | 50.6% | — |
| Berkeley Function Calling Leaderboard | — | 11.1% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Ministral 8B: 18.4 (#281)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1191 |
| DTBench | 91.2% | 45.7% |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Ministral 8B: 25.7 (#267)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| LMArena Math | 1491 | 1188 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
| MATH Level 5 | — | 14.9% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Ministral 8B: 12.6 (#297)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| GPQA Diamond | 93.1% | 27.1% |
| LMArena Expert | 1521 | 1170 |
| SimpleQA Verified | 50.6% | — |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Ministral 8B: —
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Ministral 8B: 35.1 (#247)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1466 | 1165 |
| LMArena Chinese | 1529 | 1193 |
| LMArena Russian | 1482 | 1195 |
| LMArena French | 1491 | — |
| LMArena German | 1488 | — |
| LMArena Japanese | 1487 | — |
| LMArena Korean | 1458 | — |
| LMArena Spanish | 1472 | — |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Ministral 8B: 60.5 (#250)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1483 | 1161 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Ministral 8B: 36.7 (#227)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1494 | 1212 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Ministral 8B: 39.6 (#246)
| Benchmark | Kimi K3 | Ministral 8B |
|---|---|---|
| LMArena Text | 1476 | 1191 |
| LMArena Creative Writing | 1454 | 1175 |
| LMArena Multi-Turn | 1488 | 1166 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Ministral 8B?
Kimi K3 is the stronger model overall, scoring 59.5 to 28.2 on the Noometry Index. Ministral 8B costs 40× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Ministral 8B better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 35.0 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 262K.
How many benchmarks do Kimi K3 and Ministral 8B share?
14 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Ministral 8B has 17.