Model comparison
Gemini 3.1 Flash Lite vs Kimi K2 Thinking Turbo
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 40.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 2 categories and Kimi K2 Thinking Turbo in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 41.7.
- The biggest single-benchmark swing is Chess Puzzles: 25% for Gemini 3.1 Flash Lite 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 Flash Lite | Kimi K2 Thinking Turbo | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 40.4 | 45.4 |
| Released | 2026-03-03 | 2025-11-06 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 38 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 3.1 Flash Lite: 37.5 (#179), Kimi K2 Thinking Turbo: 38.1 (#166)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena WebDev | 1256 | 1322 |
| LMArena Coding | 1400 | 1454 |
| SciCode | 41.9% | — |
| WeirdML | 52.2% | — |
| ALE-Bench | 797.73 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Flash Lite: 29.9 (#72), Kimi K2 Thinking Turbo: —
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| DeepResearch Bench | 37.3% | — |
Reasoning Kimi K2 Thinking Turbo leads
Gemini 3.1 Flash Lite: 22.3 (#181), Kimi K2 Thinking Turbo: 31.4 (#72)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| Chess Puzzles | 25% | 20% |
| LMArena Hard Prompts | 1407 | 1428 |
| Kagi LLM Benchmark | 67.2% | — |
| NYT Connections (extended) | 8.2% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
| Epoch Capabilities Index | 144.45 | — |
| ForecastBench | 54.4 | — |
Math Kimi K2 Thinking Turbo leads
Gemini 3.1 Flash Lite: 39.5 (#82), Kimi K2 Thinking Turbo: 45.5 (#62)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 83.1% |
| LMArena Math | 1427 | 1429 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
Knowledge Kimi K2 Thinking Turbo leads
Gemini 3.1 Flash Lite: 41.7 (#95), Kimi K2 Thinking Turbo: 50.9 (#64)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 81.8% | 84.2% |
| LMArena Expert | 1397 | 1439 |
| Humanity's Last Exam | 8.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 38.7 (#57), Kimi K2 Thinking Turbo: —
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Too close to call
Gemini 3.1 Flash Lite: 52.5 (#82), Kimi K2 Thinking Turbo: 51.6 (#104)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1410 | 1398 |
| LMArena Chinese | 1461 | 1457 |
| LMArena French | 1423 | 1425 |
| LMArena German | 1429 | 1390 |
| LMArena Japanese | 1411 | 1356 |
| LMArena Korean | 1393 | 1329 |
| LMArena Russian | 1420 | 1390 |
| LMArena Spanish | 1420 | 1407 |
Instruction Following Kimi K2 Thinking Turbo leads
Gemini 3.1 Flash Lite: 72.9 (#126), Kimi K2 Thinking Turbo: 74.2 (#103)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1376 | 1403 |
Long Context Too close to call
Gemini 3.1 Flash Lite: 42.5 (#117), Kimi K2 Thinking Turbo: 43.2 (#99)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1394 | 1415 |
Writing & Preference Too close to call
Gemini 3.1 Flash Lite: 61.0 (#90), Kimi K2 Thinking Turbo: 60.2 (#99)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1416 | 1415 |
| LMArena Creative Writing | 1401 | 1373 |
| LMArena Multi-Turn | 1417 | 1414 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Kimi K2 Thinking Turbo?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 40.4 on the Noometry Index.
Is Gemini 3.1 Flash Lite or Kimi K2 Thinking Turbo better for coding?
They score almost the same on coding (37.5 vs 38.1); test both on your own repository before choosing.
How many benchmarks do Gemini 3.1 Flash Lite and Kimi K2 Thinking Turbo share?
21 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Kimi K2 Thinking Turbo has 21.