Model comparison
Kimi K2.7 Code vs MiniMax-M2.5
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 3.3× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
MiniMaxSummary
- They share 4 benchmarks with published results for both. Kimi K2.7 Code scores higher in 3 categories and MiniMax-M2.5 in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.9 to 26.9.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Kimi K2.7 Code accepts more context: 262K tokens versus 205K.
Side by side
| Kimi K2.7 Code | MiniMax-M2.5 | |
|---|---|---|
| Provider | Moonshot AI | MiniMax |
| Noometry Index | 43.3 | 38.3 |
| Released | 2026-06-12 | 2026-02-12 |
| Weights | Open | Open |
| Context window | 262K | 205K |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.95 | $0.30 |
| Output $ / M tokens | $4 | $1.20 |
| Results tracked | 19 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Kimi K2.7 Code: 42.9 (#95), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1473 | 1387 |
| ALE-Bench | 886.23 | 618.17 |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| SciCode | 47.5% | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1381 |
Agentic & Tool Use MiniMax-M2.5 leads
Kimi K2.7 Code: 24.0 (#122), MiniMax-M2.5: 30.4 (#77)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| Vending-Bench 2 | 5,083 | -23.16 |
| Terminal-Bench | — | 42.7% |
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| Epoch Capabilities Index | 149.97 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | 57.9% | — |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1372 |
| Surface Evolver Bench | 48.8% | — |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | — | 4% |
| LMArena Math | — | 1378 |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.5 (#57), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| GPQA Diamond | 87.9% | — |
| SimpleQA Verified | 36.5% | — |
| Vectara Hallucination Rate | — | 9.1% |
| LMArena Expert | — | 1379 |
Multilingual Not comparable
Kimi K2.7 Code: —, MiniMax-M2.5: 47.1 (#152)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | — | 1338 |
| LMArena Chinese | — | 1393 |
| LMArena French | — | 1362 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1171 |
| LMArena Korean | — | 1232 |
| LMArena Russian | — | 1358 |
| LMArena Spanish | — | 1354 |
Instruction Following Not comparable
Kimi K2.7 Code: —, MiniMax-M2.5: 71.5 (#148)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | — | 1353 |
Long Context Not comparable
Kimi K2.7 Code: —, MiniMax-M2.5: 37.5 (#216)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
| LMArena Longer Query | — | 1366 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, MiniMax-M2.5: 53.9 (#153)
| Benchmark | Kimi K2.7 Code | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | — | 1359 |
| LMArena Creative Writing | — | 1331 |
| EQ-Bench Creative Writing | — | 1361 |
| LMArena Multi-Turn | — | 1364 |
Frequently asked questions
Is Kimi K2.7 Code better than MiniMax-M2.5?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 3.3× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.7 Code or MiniMax-M2.5?
MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.
Is Kimi K2.7 Code or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 42.9 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.7 Code does, with 262K tokens against 205K.
How many benchmarks do Kimi K2.7 Code and MiniMax-M2.5 share?
4 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and MiniMax-M2.5 has 33.