Compare / MiniMax vs Moonshot AI
MiniMax vs Moonshot AI: which AI lab is ahead?
Each lab's best model on sale goes head to head on every kind of work we measure, from our own benchmarks and licensed sources. 12 models in all; a lab is only as good as the model you would actually pick from it.
Kinds of work led by each lab's best model there, of the 5 both are measured on.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe). Models on sale means listed on OpenRouter today.
MiniMax or Moonshot AI? The short answer
Moonshot AI is ahead: its best models beat MiniMax's in all 5 kinds of work both are measured on.
- Pick Moonshot AI for agents and tool use, professional work, reasoning and knowledge, writing and sticking to the facts.
- Moonshot AI's Kimi K3 is #10 on our overall leaderboard; no MiniMax model has enough of our results to be ranked there yet.
- Prices start at $0.52 per million tokens for MiniMax (MiniMax-M3) and $1.00 for Moonshot AI (Kimi K2 (0711)).
Head to head
Each line names the model behind the number. Prices are blended, three input tokens to one output, at the developer's list price where we have read it; see every model's price. Intelligence Index from Artificial Analysis; overall score from our leaderboard.
Which lab is better for what
For each kind of work, each lab's best model there and its rank among every model on sale. Further right is better; the better rank is in green.
Every model, by intelligence and price
Each dot is a model on sale with an Intelligence Index from Artificial Analysis. Up is smarter; left is cheaper. Hover or tap a dot for its name.
MiniMaxMoonshot AI
On our overall leaderboard
The 1 of their models we rank overall: one score out of 100 across everything we publish (how the score works). Only models with enough of our own results are ranked.
- #10Kimi K350
Benchmark by benchmark
The headline result of every benchmark both labs have models on: each lab's best model and its rank among the models on sale. Green marks the better rank.
| Measure | MiniMax | Moonshot AI |
|---|---|---|
| Agents and tool use | ||
| OpenHands Index · Average% resolved, higher is better | 57.2%MiniMax-M3 · 13 of 33 | 57.1%Kimi K2.6 · 14 of 33 |
| Artificial Analysis · Terminal-Bench 4.0% of tasks, higher is better | 2.0%MiniMax-M3 · 44 of 105 | 12.6%Kimi K3 · 29 of 105 |
| Artificial Analysis · Terminal-Bench 2.1% of tasks, higher is better | 65.2%MiniMax-M3 · 37 of 115 | 85.0%Kimi K3 · 11 of 115 |
| Artificial Analysis · τ-bench banking% of tasks, higher is better | 15.3%MiniMax-M3 · 55 of 113 | 46.0%Kimi K3 · 9 of 113 |
| Vending-Bench 2 · Money after a yearUS dollars, higher is better | $2,158MiniMax-M3 · 39 of 56 | $6,205Kimi K2.6 · 15 of 56 |
| Professional work | ||
| APEX-Agents · Tasks passed% of tasks, higher is better | 37.7%MiniMax-M3 · 30 of 37 | 50.6%Kimi K3 · 21 of 37 |
| Reasoning and knowledge | ||
| Artificial Analysis · Artificial Analysis Intelligence Indexindex score, higher is better | 29.2MiniMax-M3 · 50 of 198 | 43.6Kimi K3 · 16 of 198 |
| Artificial Analysis · Humanity's Last Exam% of questions, higher is better | 39.0%MiniMax-M3 · 41 of 197 | 46.9%Kimi K3 · 16 of 197 |
| Artificial Analysis · GPQA Diamond% of questions, higher is better | 92.9%MiniMax-M3 · 14 of 187 | 93.5%Kimi K3 · 10 of 187 |
| Sticking to the facts | ||
| Vectara Hallucination Leaderboard · Hallucination rate · Vectara% of summaries, lower is better | 9.1%MiniMax-M2.5 · 34 of 79 | 10.8%Kimi K2.6 · 52 of 79 |
| Arena (formerly LMArena) · Overall · Text factualityArena rating, higher is better | 1,434MiniMax-M3 · 69 of 113 | 1,472Kimi K3 · 16 of 113 |
| Writing | ||
| Arena (formerly LMArena) · Overall · TextArena rating, higher is better | 1,440MiniMax-M3 · 63 of 166 | 1,488Kimi K3 · 11 of 166 |
| UGI Leaderboard · Writing score · UGIscore out of 100, higher is better | 41.7MiniMax-M2.5 · 80 of 138 | 64.4Kimi K2.6 · 25 of 138 |
Quick answers
Is MiniMax or Moonshot AI better?
Moonshot AI is ahead: its best models beat MiniMax's in all 5 kinds of work both are measured on.
What is MiniMax's best model?
MiniMax-M3: 29.2 on the Artificial Analysis Intelligence Index.
What is Moonshot AI's best model?
Kimi K3: #10 on the Spring Prompt overall leaderboard and 43.6 on the Artificial Analysis Intelligence Index.
Which is better for agents and tool use, MiniMax or Moonshot AI?
Moonshot AI: its best model there, Kimi K2 (0711), ranks 19 of 164 models on sale, against 74 for MiniMax's MiniMax-M3.
Which is better for reasoning and knowledge, MiniMax or Moonshot AI?
Moonshot AI: its best model there, Kimi K3, ranks 15 of 198 models on sale, against 38 for MiniMax's MiniMax-M3.
Which is better for writing, MiniMax or Moonshot AI?
Moonshot AI: its best model there, Kimi K3, ranks 11 of 188 models on sale, against 66 for MiniMax's MiniMax-M3.
Which is cheaper, MiniMax or Moonshot AI?
MiniMax's cheapest model with results, MiniMax-M3, costs $0.52 per million tokens (three input to one output), against $1.00 for Kimi K2 (0711) from Moonshot AI.
Other labs compared
- Moonshot AI vs OpenAIBest model against best model
- Anthropic vs Moonshot AIBest model against best model
- Google vs Moonshot AIBest model against best model
- Moonshot AI vs xAIBest model against best model
- Meta vs Moonshot AIBest model against best model
- DeepSeek vs Moonshot AIBest model against best model
- Alibaba vs Moonshot AIBest model against best model
- Mistral AI vs Moonshot AIBest model against best model
Which model is best for your product?
Benchmarks aren't your data. We test the models from MiniMax, Moonshot AI and the rest on your own tasks, with the cost of every answer.