Model comparison
Gemini 3.1 Pro Preview vs Kimi K2 (Jul 2025)
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.9 on the Noometry Index. Kimi K2 (Jul 2025) costs 4.5× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
GoogleSummary
- They share 30 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Kimi K2 (Jul 2025) in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 22.7.
- The biggest single-benchmark swing is SimpleBench: 79.6% for Gemini 3.1 Pro Preview and 26.3% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 56.7 | 40.9 |
| Released | 2026-02-19 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $2 | $0.57 |
| Output $ / M tokens | $12 | $2.30 |
| Results tracked | 71 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.1 Pro Preview: 42.7 (#88), Kimi K2 (Jul 2025): 43.1 (#83)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| GSO | 22.6% | 4.9% |
| WeirdML | 72.1% | 42.8% |
| LMArena Coding | 1483 | 1399 |
| ALE-Bench | 1,161 | 597.5 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1446 | — |
| SciCode | 58.9% | — |
| MirrorCode | 8.9% | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 37.7 (#33), Kimi K2 (Jul 2025): 32.2 (#59)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | 80.2% | 35.7% |
| METR Time Horizons | 77% | 59.2% |
| APEX-Agents | 35.3% | — |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#9), Kimi K2 (Jul 2025): 22.7 (#173)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | 79.6% | 26.3% |
| LMArena Hard Prompts | 1484 | 1384 |
| Epoch Capabilities Index | 154.92 | 146.02 |
| ForecastBench | 59 | 60.2 |
| ARC-AGI-2 | 77.1% | — |
| Kagi LLM Benchmark | — | 64.4% |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 61.8 (#28), Kimi K2 (Jul 2025): 40.1 (#81)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1485 | 1396 |
| FrontierMath (Feb 2025 set) | 36.9% | 21.4% |
| FrontierMath Tier 4 (v1) | 16.7% | 0% |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| Omni-MATH | — | 65.4% |
Knowledge Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.8 (#3), Kimi K2 (Jul 2025): 36.9 (#153)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| Vectara Hallucination Rate | 10.4% | 17.9% |
| LMArena Expert | 1484 | 1363 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
Gemini 3.1 Pro Preview: 38.1 (#60), Kimi K2 (Jul 2025): —
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| 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: 57.1 (#11), Kimi K2 (Jul 2025): 49.8 (#125)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1475 | 1372 |
| LMArena Chinese | 1528 | 1416 |
| LMArena French | 1488 | 1379 |
| LMArena German | 1491 | 1386 |
| LMArena Japanese | 1494 | 1349 |
| LMArena Korean | 1458 | 1324 |
| LMArena Russian | 1496 | 1384 |
| LMArena Spanish | 1480 | 1383 |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.1 (#31), Kimi K2 (Jul 2025): 71.3 (#151)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1465 | 1347 |
| IFEval | — | 85% |
Long Context Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 47.3 (#17), Kimi K2 (Jul 2025): 41.2 (#140)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| CL-bench | 20.8% | 17.6% |
| LMArena Longer Query | 1482 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.3 (#36), Kimi K2 (Jul 2025): 62.5 (#76)
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1480 | 1380 |
| LMArena Creative Writing | 1482 | 1349 |
| EQ-Bench Creative Writing | 1491 | 1666 |
| LMArena Multi-Turn | 1486 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |
| EQ-Bench 4 | 1142 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Kimi K2 (Jul 2025)?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.9 on the Noometry Index. Kimi K2 (Jul 2025) costs 4.5× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Pro Preview or Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is Gemini 3.1 Pro Preview or Kimi K2 (Jul 2025) better for coding?
They score almost the same on coding (42.7 vs 43.1); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.1 Pro Preview and Kimi K2 (Jul 2025) share?
30 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Kimi K2 (Jul 2025) has 42.