Model comparison
Gemini 3.1 Flash Lite vs Kimi K2 (Jul 2025)
Gemini 3.1 Flash Lite and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (40.8 vs 41.2), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 4 categories and Kimi K2 (Jul 2025) in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Kimi K2 (Jul 2025) leads 42.4 to 37.8.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 8.2% for Gemini 3.1 Flash Lite and 17.9% for Kimi K2 (Jul 2025).
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Gemini 3.1 Flash Lite 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 Flash Lite | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 40.8 | 41.2 |
| Released | 2026-03-03 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.25 | $0.57 |
| Output $ / M tokens | $1.50 | $2.30 |
| Results tracked | 38 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Gemini 3.1 Flash Lite: 37.8 (#188), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| WeirdML | 52.2% | 42.8% |
| LMArena Coding | 1400 | 1399 |
| ALE-Bench | 797.73 | 597.5 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1256 | — |
| SciCode | 41.9% | — |
| GSO | — | 4.9% |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Gemini 3.1 Flash Lite: 30.2 (#79), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| DeepResearch Bench | 37.3% | — |
| METR Time Horizons | — | 59.2% |
Reasoning Too close to call
Gemini 3.1 Flash Lite: 22.9 (#186), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 67.2% | 64.4% |
| LMArena Hard Prompts | 1407 | 1384 |
| Epoch Capabilities Index | 144.47 | 146.01 |
| ForecastBench | 54.4 | 60.2 |
| SimpleBench | — | 26.3% |
| NYT Connections (extended) | 8.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 25% | — |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| DTBench | 76.8% | — |
| LMCA | 35% | — |
Math Kimi K2 (Jul 2025) leads
Gemini 3.1 Flash Lite: 40.7 (#90), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1428 | 1397 |
| FrontierMath (Tiers 1-3) | 27.7% | — |
| OTIS Mock AIME 2024-2025 | 80% | — |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 41.9 (#104), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| Vectara Hallucination Rate | 8.2% | 17.9% |
| LMArena Expert | 1398 | 1365 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 8.6% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| GPQA (HELM) | — | 65.3% |
Multimodal Not comparable
Gemini 3.1 Flash Lite: 39.4 (#60), Kimi K2 (Jul 2025): —
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1240 | — |
Multilingual Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 52.3 (#86), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1411 | 1372 |
| LMArena Chinese | 1461 | 1415 |
| LMArena French | 1424 | 1379 |
| LMArena German | 1429 | 1387 |
| LMArena Japanese | 1413 | 1349 |
| LMArena Korean | 1392 | 1325 |
| LMArena Russian | 1420 | 1385 |
| LMArena Spanish | 1421 | 1386 |
Instruction Following Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 72.7 (#131), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1377 | 1348 |
| IFEval | — | 85% |
Long Context Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 42.5 (#122), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Longer Query | 1394 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Gemini 3.1 Flash Lite: 60.9 (#94), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1416 | 1380 |
| LMArena Creative Writing | 1401 | 1350 |
| LMArena Multi-Turn | 1417 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Kimi K2 (Jul 2025)?
Gemini 3.1 Flash Lite and Kimi K2 (Jul 2025) score almost the same on the Noometry Index (40.8 vs 41.2), so choose on price, context window or the category you care about most.
Which is cheaper, Gemini 3.1 Flash Lite or Kimi K2 (Jul 2025)?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is Gemini 3.1 Flash Lite or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.1 Flash Lite and Kimi K2 (Jul 2025) share?
23 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Kimi K2 (Jul 2025) has 42.