Model comparison
Gemini 2.5 Flash-Lite vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 5.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 0 categories and Kimi K2 (Jul 2025) in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Kimi K2 (Jul 2025) leads 41.2 to 33.3.
- The biggest single-benchmark swing is GPQA (HELM): 30.9% for Gemini 2.5 Flash-Lite and 65.3% for Kimi K2 (Jul 2025).
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Gemini 2.5 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 2.5 Flash-Lite | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | Moonshot AI | |
| Noometry Index | 37.0 | 41.2 |
| Released | 2025-06-17 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 262K |
| Input $ / M tokens | $0.10 | $0.57 |
| Output $ / M tokens | $0.40 | $2.30 |
| Results tracked | 33 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 38.5 (#173), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| WeirdML | 35.2% | 42.8% |
| LMArena Coding | 1373 | 1399 |
| ALE-Bench | 325.9 | 597.5 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 28.0 (#96), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 59.1% |
| Terminal-Bench | — | 35.7% |
| METR Time Horizons | — | 59.2% |
Reasoning Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 22.2 (#205), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 64.4% |
| LMArena Hard Prompts | 1377 | 1384 |
| Epoch Capabilities Index | 133.94 | 146.01 |
| SimpleBench | — | 26.3% |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
| ForecastBench | — | 60.2 |
Math Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 38.0 (#144), Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | 48% | 65.4% |
| LMArena Math | 1373 | 1397 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 32.5 (#210), Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | 53.7% | 81.9% |
| Vectara Hallucination Rate | 3.3% | 17.9% |
| GPQA (HELM) | 30.9% | 65.3% |
| LMArena Expert | 1373 | 1365 |
| Confabulations | — | 20.4% |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 29.1 (#114), Kimi K2 (Jul 2025): —
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual Too close to call
Gemini 2.5 Flash-Lite: 49.3 (#134), Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1369 | 1372 |
| LMArena Chinese | 1404 | 1415 |
| LMArena French | 1388 | 1379 |
| LMArena German | 1389 | 1387 |
| LMArena Japanese | 1359 | 1349 |
| LMArena Korean | 1360 | 1325 |
| LMArena Russian | 1373 | 1385 |
| LMArena Spanish | 1396 | 1386 |
Instruction Following Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 70.0 (#168), Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | 81% | 85% |
| LMArena Instruction Following | 1367 | 1348 |
Long Context Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 33.3 (#262), Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | 47.2% | 66.7% |
| LMArena Longer Query | 1373 | 1353 |
| CL-bench | — | 17.6% |
Writing & Preference Kimi K2 (Jul 2025) leads
Gemini 2.5 Flash-Lite: 56.8 (#135), Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Gemini 2.5 Flash-Lite | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1379 | 1380 |
| LMArena Creative Writing | 1367 | 1350 |
| WildBench | 81.8% | 86.2% |
| LMArena Multi-Turn | 1366 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 5.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash-Lite or Kimi K2 (Jul 2025)?
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 (Jul 2025) lists at $0.57 and $2.30.
Is Gemini 2.5 Flash-Lite or Kimi K2 (Jul 2025) better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 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 (Jul 2025) share?
29 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Kimi K2 (Jul 2025) has 42.