Model comparison
Gemini 3.1 Flash Lite vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
GoogleSummary
- They share 31 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 1 category and Kimi K3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 22.9.
- The biggest single-benchmark swing is NYT Connections (extended): 8.2% for Gemini 3.1 Flash Lite and 93.6% for Kimi K3.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Flash Lite | Kimi K3 | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 40.8 | 59.5 |
| Released | 2026-03-03 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 1.05M |
| Input $ / M tokens | $0.25 | $3 |
| Output $ / M tokens | $1.50 | $15 |
| Results tracked | 38 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Gemini 3.1 Flash Lite: 37.8 (#188), Kimi K3: 61.0 (#10)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| LMArena WebDev | 1256 | 1654 |
| SciCode | 41.9% | 59.5% |
| WeirdML | 52.2% | 82.6% |
| LMArena Coding | 1400 | 1508 |
| ALE-Bench | 797.73 | 1,524 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| FrontierSWE | — | 25.9% |
Agentic & Tool Use Kimi K3 leads
Gemini 3.1 Flash Lite: 30.2 (#79), Kimi K3: 41.8 (#20)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| DeepResearch Bench | 37.3% | — |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |
Reasoning Kimi K3 leads
Gemini 3.1 Flash Lite: 22.9 (#186), Kimi K3: 63.0 (#17)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| NYT Connections (extended) | 8.2% | 93.6% |
| CritPt | 1.1% | 23.4% |
| Chess Puzzles | 25% | 39% |
| LMArena Hard Prompts | 1407 | 1496 |
| DTBench | 76.8% | 91.2% |
| LMCA | 35% | 52.7% |
| Epoch Capabilities Index | 144.47 | 157.45 |
| ForecastBench | 54.4 | 61.1 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | — | 60.7% |
| Kagi LLM Benchmark | 67.2% | — |
| ARC-AGI-1 | — | 94.5% |
| EnigmaEval | 3% | — |
| Thematic Generalization | 63.3% | — |
| Mystery Game Puzzles | — | 26% |
| Surface Evolver Bench | — | 95% |
Math Kimi K3 leads
Gemini 3.1 Flash Lite: 40.7 (#90), Kimi K3: 74.2 (#16)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 27.7% | 72.2% |
| OTIS Mock AIME 2024-2025 | 80% | 97.2% |
| LMArena Math | 1428 | 1491 |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| ProofBench | — | 87% |
Knowledge Kimi K3 leads
Gemini 3.1 Flash Lite: 41.9 (#104), Kimi K3: 63.2 (#21)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| GPQA Diamond | 81.8% | 93.1% |
| LMArena Expert | 1398 | 1521 |
| Humanity's Last Exam | 8.6% | — |
| SimpleQA Verified | — | 50.6% |
| Vectara Hallucination Rate | 8.2% | — |
Multimodal Gemini 3.1 Flash Lite leads
Gemini 3.1 Flash Lite: 39.4 (#60), Kimi K3: 37.8 (#70)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| LMArena Vision | 1240 | — |
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
Gemini 3.1 Flash Lite: 52.3 (#86), Kimi K3: 56.3 (#21)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1411 | 1466 |
| LMArena Chinese | 1461 | 1529 |
| LMArena French | 1424 | 1491 |
| LMArena German | 1429 | 1488 |
| LMArena Japanese | 1413 | 1487 |
| LMArena Korean | 1392 | 1458 |
| LMArena Russian | 1420 | 1482 |
| LMArena Spanish | 1421 | 1472 |
Instruction Following Kimi K3 leads
Gemini 3.1 Flash Lite: 72.7 (#131), Kimi K3: 77.7 (#14)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1377 | 1483 |
Long Context Kimi K3 leads
Gemini 3.1 Flash Lite: 42.5 (#122), Kimi K3: 45.8 (#29)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1394 | 1494 |
Writing & Preference Kimi K3 leads
Gemini 3.1 Flash Lite: 60.9 (#94), Kimi K3: 76.6 (#4)
| Benchmark | Gemini 3.1 Flash Lite | Kimi K3 |
|---|---|---|
| LMArena Text | 1416 | 1476 |
| LMArena Creative Writing | 1401 | 1454 |
| LMArena Multi-Turn | 1417 | 1488 |
| EQ-Bench Creative Writing | — | 2082 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is Gemini 3.1 Flash Lite better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 11× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Flash Lite or Kimi K3?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Kimi K3 lists at $3 and $15.
Is Gemini 3.1 Flash Lite or Kimi K3 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Gemini 3.1 Flash Lite and Kimi K3 share?
31 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Kimi K3 has 53.