Model comparison
Kimi K3 vs MiniMax M1
Kimi K3 is the stronger model overall, scoring 59.5 to 40.3 on the Noometry Index. MiniMax M1 costs 6.2× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMaxSummary
- They share 17 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and MiniMax M1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 37.5.
- MiniMax M1 is cheaper at $0.55 / $2.20 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 1M.
Side by side
| Kimi K3 | MiniMax M1 | |
|---|---|---|
| Provider | Moonshot AI | MiniMax |
| Noometry Index | 59.5 | 40.3 |
| Released | 2026-07-16 | 2025-06-13 |
| Weights | Open | Open |
| Context window | 1.05M | 1M |
| Max output | 1.05M | 40K |
| Input $ / M tokens | $3 | $0.55 |
| Output $ / M tokens | $15 | $2.20 |
| Results tracked | 53 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), MiniMax M1: 39.9 (#153)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Coding | 1508 | 1359 |
| 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 Not comparable
Kimi K3: 41.8 (#20), MiniMax M1: —
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| APEX-Agents | 50.6% | — |
| 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), MiniMax M1: 26.9 (#126)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1339 |
| 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% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), MiniMax M1: 37.5 (#151)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Math | 1491 | 1361 |
| 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% | — |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), MiniMax M1: 36.4 (#170)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Expert | 1521 | 1317 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
Multimodal Not comparable
Kimi K3: 37.8 (#70), MiniMax M1: —
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), MiniMax M1: 45.8 (#163)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Non-English | 1466 | 1319 |
| LMArena Chinese | 1529 | 1360 |
| LMArena French | 1491 | 1370 |
| LMArena German | 1488 | 1350 |
| LMArena Japanese | 1487 | 1217 |
| LMArena Korean | 1458 | 1266 |
| LMArena Russian | 1482 | 1329 |
| LMArena Spanish | 1472 | 1353 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), MiniMax M1: 69.3 (#174)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | 1483 | 1312 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), MiniMax M1: 41.4 (#141)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Longer Query | 1494 | 1326 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), MiniMax M1: 53.1 (#161)
| Benchmark | Kimi K3 | MiniMax M1 |
|---|---|---|
| LMArena Text | 1476 | 1343 |
| LMArena Creative Writing | 1454 | 1298 |
| LMArena Multi-Turn | 1488 | 1335 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than MiniMax M1?
Kimi K3 is the stronger model overall, scoring 59.5 to 40.3 on the Noometry Index. MiniMax M1 costs 6.2× 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 MiniMax M1?
MiniMax M1 is cheaper. It lists at $0.55 per million input tokens and $2.20 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or MiniMax M1 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 1M.
How many benchmarks do Kimi K3 and MiniMax M1 share?
17 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and MiniMax M1 has 18.