Model comparison
Gemini 3 Deep Think vs MiniMax-M2
MiniMax-M2 has enough public results to be ranked (#204); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Google
MiniMaxSummary
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 19.4.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3 Deep Think | MiniMax-M2 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 58.3 | 37.4 |
| Released | 2026-02-12 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 3 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 39.3 (#159)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| LMArena Coding | — | 1370 |
Agentic & Tool Use Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Gemini 3 Deep Think leads
Gemini 3 Deep Think: 70.2 (#14), MiniMax-M2: 19.4 (#258)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| ARC-AGI-2 | 84.6% | — |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 96% | — |
| CritPt | 25.7% | — |
| LMArena Hard Prompts | — | 1357 |
Math Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 37.3 (#160)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| LMArena Math | — | 1352 |
Knowledge Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 37.0 (#163)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| LMArena Expert | — | 1337 |
Multilingual Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 45.3 (#171)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1366 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1326 |
Instruction Following Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 70.2 (#166)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |
Long Context Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 40.5 (#153)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1331 |
Writing & Preference Not comparable
Gemini 3 Deep Think: —, MiniMax-M2: 53.0 (#162)
| Benchmark | Gemini 3 Deep Think | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1286 |
| LMArena Multi-Turn | — | 1361 |
Frequently asked questions
Is Gemini 3 Deep Think better than MiniMax-M2?
MiniMax-M2 has enough public results to be ranked (#204); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Gemini 3 Deep Think and MiniMax-M2 share?
0 benchmarks have published results for both models. Gemini 3 Deep Think has 3 scored results on Noometry and MiniMax-M2 has 21.