Model comparison
Kimi K2 vs MiniMax M3
Head-to-head evidence from 13 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: Kimi K2 unranked; MiniMax M3 #18
BenchAlign evidence: Kimi K2 supported; MiniMax M3 supported. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Kimi K2 and MiniMax M3 share 13 comparable benchmark results. 1 of 8 categories are comparable. 2 results are unique to Kimi K2; 32 to MiniMax M3.
Updated July 16, 2026- Shared results
- 13
- Kimi K2 only
- 2
- MiniMax M3 only
- 32
- Comparable categories
- 1 / 8
Pick MiniMax M3 if you want the stronger benchmark profile. Kimi K2 only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Confidence note. This is a partial-evidence comparison with 13 shared benchmark results across 6 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
MiniMax M3 is clearly ahead on the provisional aggregate, 70 to 43. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiniMax M3's sharpest advantage is in mathematics, where it averages 85.7 against 16.1.
Kimi K2 is also the more expensive model on tokens at $0.60 input / $2.50 output per 1M tokens, versus $0.30 input / $1.20 output per 1M tokens for MiniMax M3. That is roughly 2.1x on output cost alone. MiniMax M3 gives you the larger context window at 1M, compared with 128K for Kimi K2.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Kimi K2 | Δ | MiniMax M3 |
|---|---|---|---|
| Math | Kimi K216.1 | Margin→ 69.6 | MiniMax M385.7 |
| Agentic | Kimi K2Not measured | MarginNo overlap | MiniMax M372.3 |
| Coding | Kimi K2Not measured | MarginNo overlap | MiniMax M372.2 |
| Multimodal | Kimi K2Not measured | MarginNo overlap | MiniMax M364.9 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Kimi K2 | MiniMax M3 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Kimi K2$0.6 input / $2.5 output | MiniMax M3$0.3 input / $1.2 output | MiniMax M3 has the lower combined listed price. |
| Generation speedtokens per second | Kimi K243 tok/s | MiniMax M3Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Kimi K21.51 s | MiniMax M3Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Kimi K2128K | MiniMax M31M | MiniMax M3 lists the larger context window. |
Benchmark Deep Dive
Agentic16 benchmarks
| Benchmark | Kimi K2 | MiniMax M3 | Result |
|---|---|---|---|
| τ²-bench resultsSource | 61.1% | 88.9% | MiniMax M3 leads |
| Terminal-Bench 2.0Source | — | 66% | Not comparable |
| BrowseCompSource | — | 83.5% | Not comparable |
| OSWorld-VerifiedSource | — | 70.1% | Not comparable |
| MCP AtlasSource | — | 74.2% | Not comparable |
| Claw-EvalSource | — | 74.5% | Not comparable |
| AA Agentic IndexSource | — | 35.4% | Not comparable |
| GDPval-AASource | — | 44.7% | Not comparable |
| GDPval-AASource | — | 1395 | Not comparable |
| GDPval rubricsSource | — | 74.7% | Not comparable |
| BankerToolBenchSource | — | 76.1% | Not comparable |
| ResearchClawBenchSource | — | 19.8% | Not comparable |
| OSWorld 2.0Source | — | 4.6% | Not comparable |
| AA BriefcaseSource | — | 1110 | Not comparable |
| AA EnterpriseOps-GymSource | — | 32.1% | Not comparable |
| AA Harvey LABSource | — | 6.7% | Not comparable |
Coding11 benchmarks
| Benchmark | Kimi K2 | MiniMax M3 | Result |
|---|---|---|---|
| Terminal-Bench HardSource | 15.9% | 42.4% | MiniMax M3 leads |
| AA-SciCodeSource | 34.5% | 45.4% | MiniMax M3 leads |
| SWE-bench VerifiedSource | — | 80.5% | Not comparable |
| SWE-bench ProSource | — | 59% | Not comparable |
| Terminal-Bench 2.0Source | — | 66.0% | Not comparable |
| NL2RepoSource | — | 42.1% | Not comparable |
| AA Coding IndexSource | — | 58.6% | Not comparable |
| VIBE V2Source | — | 50.1% | Not comparable |
| SVG-BenchSource | — | 63.7% | Not comparable |
| KernelBench HardSource | — | 28.8% | Not comparable |
| AA Terminal-Bench 2.1Source | — | 65.2% | Not comparable |
Reasoning2 benchmarks
Knowledge7 benchmarks
| Benchmark | Kimi K2 | MiniMax M3 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 19.4% | 44.4% | MiniMax M3 leads |
| AA-GPQA DiamondSource | 76.6% | 92.9% | MiniMax M3 leads |
| AA-HLESource | 7.0% | 37.1% | MiniMax M3 leads |
| AA-Omniscience IndexSource | -27.5% | 1.4% | MiniMax M3 leads |
| AA-Omniscience AccuracySource | 26.8% | 15.0% | Kimi K2 leads |
| AA-Omniscience Hallucination RateSource | 74.2% | 16.1% | MiniMax M3 leads |
| AA Openness IndexSource | — | 33.3% | Not comparable |
MathMiniMax M3 wins3 benchmarks
Multimodal7 benchmarks
| Benchmark | Kimi K2 | MiniMax M3 | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1085 | 1294 | MiniMax M3 leads |
| OfficeQA ProSource | — | 45.1% | Not comparable |
| OmniDocBench 1.5Source | — | 91.6% | Not comparable |
| MMMU-ProSource | — | 78.1% | Not comparable |
| VideoMMMUSource | — | 84.6% | Not comparable |
| Video-MME (with subtitle)Source | — | 85.4% | Not comparable |
| AA-MMMU-ProSource | — | 78.6% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Kimi K2 | MiniMax M3 | Result |
|---|---|---|---|
| AA-IFBenchSource | 41.5% | 82.9% | MiniMax M3 leads |
Frequently Asked Questions (2)
Which is better, Kimi K2 or MiniMax M3?
MiniMax M3 is ahead on BenchLM's provisional leaderboard, 70 to 43.
Which is better for math, Kimi K2 or MiniMax M3?
MiniMax M3 has the edge for math in this comparison, averaging 85.7 versus 16.1. Kimi K2 stays close enough that the answer can still flip depending on your workload.
Related Comparisons
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.