Model comparison
Gemini 3.1 Pro Preview vs Kimi K2 Thinking Turbo
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Kimi K2 Thinking Turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 32.5.
- The biggest single-benchmark swing is Chess Puzzles: 55% for Gemini 3.1 Pro Preview and 20% for Kimi K2 Thinking Turbo.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 56.7 | 45.8 |
| Released | 2026-02-19 | 2025-11-06 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 71 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 42.5 (#99), Kimi K2 Thinking Turbo: 38.4 (#178)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena WebDev | 1447 | 1322 |
| LMArena Coding | 1484 | 1454 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Pro Preview: 37.7 (#34), Kimi K2 Thinking Turbo: —
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#12), Kimi K2 Thinking Turbo: 32.5 (#75)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 55% | 20% |
| LMArena Hard Prompts | 1485 | 1428 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.77 | — |
| ForecastBench | 59 | — |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 62.1 (#34), Kimi K2 Thinking Turbo: 47.4 (#68)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 83.1% |
| LMArena Math | 1485 | 1429 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.8 (#3), Kimi K2 Thinking Turbo: 50.9 (#69)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 94.4% | 84.2% |
| LMArena Expert | 1485 | 1439 |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |
Multimodal Not comparable
Gemini 3.1 Pro Preview: 37.9 (#69), Kimi K2 Thinking Turbo: —
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 57.0 (#12), Kimi K2 Thinking Turbo: 51.4 (#109)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1477 | 1398 |
| LMArena Chinese | 1529 | 1456 |
| LMArena French | 1487 | 1425 |
| LMArena German | 1491 | 1390 |
| LMArena Japanese | 1493 | 1357 |
| LMArena Korean | 1455 | 1330 |
| LMArena Russian | 1498 | 1391 |
| LMArena Spanish | 1479 | 1406 |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.0 (#32), Kimi K2 Thinking Turbo: 74.0 (#109)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1466 | 1403 |
Long Context Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 47.4 (#18), Kimi K2 Thinking Turbo: 43.2 (#102)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1483 | 1415 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.1 (#37), Kimi K2 Thinking Turbo: 60.0 (#104)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1481 | 1415 |
| LMArena Creative Writing | 1482 | 1374 |
| LMArena Multi-Turn | 1488 | 1414 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Kimi K2 Thinking Turbo?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 45.8 on the Noometry Index.
Is Gemini 3.1 Pro Preview or Kimi K2 Thinking Turbo better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 38.4 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Pro Preview and Kimi K2 Thinking Turbo share?
21 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Kimi K2 Thinking Turbo has 21.