Model comparison
Gemini 2.5 Flash-Lite vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 9.8× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 1 category and Kimi K2.6 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.6 leads 54.0 to 32.5.
- The biggest single-benchmark swing is DTBench: 62.8% for Gemini 2.5 Flash-Lite and 90.9% for Kimi K2.6.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Kimi K2.6 | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 37.0 | 47.7 |
| Released | 2025-06-17 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.10 | $0.95 |
| Output $ / M tokens | $0.40 | $4 |
| Results tracked | 33 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 38.5 (#173), Kimi K2.6: 50.7 (#43)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| WeirdML | 35.2% | 55.9% |
| LMArena Coding | 1373 | 1488 |
| ALE-Bench | 325.9 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
Agentic & Tool Use Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 28.0 (#96), Kimi K2.6: 21.9 (#137)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 22.2 (#205), Kimi K2.6: 40.5 (#55)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1470 |
| DTBench | 62.8% | 90.9% |
| LMCA | 18.1% | 37.3% |
| Epoch Capabilities Index | 133.94 | 151.05 |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
Math Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 38.0 (#144), Kimi K2.6: 57.0 (#41)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1373 | 1475 |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| Omni-MATH | 48% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 32.5 (#210), Kimi K2.6: 54.0 (#54)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 10.8% |
| LMArena Expert | 1373 | 1491 |
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 29.1 (#114), Kimi K2.6: 31.6 (#103)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1198 | 1283 |
| VPCT | 30% | — |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 49.3 (#134), Kimi K2.6: 54.9 (#37)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1369 | 1446 |
| LMArena Chinese | 1404 | 1521 |
| LMArena French | 1388 | 1471 |
| LMArena German | 1389 | 1450 |
| LMArena Japanese | 1359 | 1443 |
| LMArena Korean | 1360 | 1427 |
| LMArena Russian | 1373 | 1446 |
| LMArena Spanish | 1396 | 1464 |
Instruction Following Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 70.0 (#168), Kimi K2.6: 76.3 (#43)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1451 |
| IFEval | 81% | — |
Long Context Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 33.3 (#262), Kimi K2.6: 44.9 (#52)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1373 | 1468 |
| Fiction.LiveBench | 47.2% | — |
Writing & Preference Kimi K2.6 leads
Gemini 2.5 Flash-Lite: 56.8 (#135), Kimi K2.6: 68.5 (#26)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1379 | 1455 |
| LMArena Creative Writing | 1367 | 1434 |
| LMArena Multi-Turn | 1366 | 1453 |
| EQ-Bench Creative Writing | — | 1725 |
| WildBench | 81.8% | — |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 9.8× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or Kimi K2.6?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Gemini 2.5 Flash-Lite or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 38.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Flash-Lite and Kimi K2.6 share?
24 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Kimi K2.6 has 51.