Model comparison
Kimi K2.5 vs Qwen3 8B
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.7 on the Noometry Index. Qwen3 8B costs 2.9× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Kimi K2.5 scores higher in 6 categories and Qwen3 8B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 36.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Kimi K2.5 and 56.1% for Qwen3 8B.
- Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 131K.
Side by side
| Kimi K2.5 | Qwen3 8B | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 48.1 | 33.7 |
| Released | 2026-01-27 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.45 | $0.18 |
| Output $ / M tokens | $2.25 | $0.70 |
| Results tracked | 51 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Kimi K2.5: 48.8 (#53), Qwen3 8B: 34.0 (#248)
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| SciCode | 49% | 22.6% |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| WeirdML | 45.6% | — |
| LMArena Coding | 1474 | — |
| ALE-Bench | 821.65 | — |
Agentic & Tool Use Kimi K2.5 leads
Kimi K2.5: 34.2 (#48), Qwen3 8B: 30.2 (#78)
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| Berkeley Function Calling Leaderboard | — | 42.6% |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Kimi K2.5 leads
Kimi K2.5: 31.2 (#80), Qwen3 8B: 16.6 (#303)
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| CritPt | 3.1% | 0% |
| Chess Puzzles | 12% | 5% |
| Epoch Capabilities Index | 148.03 | 136.17 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| Kagi LLM Benchmark | 78.5% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| LMArena Hard Prompts | 1453 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Qwen3 8B: 34.9 (#191)
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 56.1% |
| MathArena Final-Answer Competitions | 62.3% | — |
| LMArena Math | 1470 | — |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Qwen3 8B: 36.1 (#173)
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 87.6% | 56.8% |
| Vectara Hallucination Rate | 14.2% | 4.8% |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| LMArena Expert | 1466 | — |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Qwen3 8B: —
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Not comparable
Kimi K2.5: 53.9 (#53), Qwen3 8B: —
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1433 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1454 | — |
| LMArena German | 1441 | — |
| LMArena Japanese | 1421 | — |
| LMArena Korean | 1410 | — |
| LMArena Russian | 1435 | — |
| LMArena Spanish | 1450 | — |
Instruction Following Not comparable
Kimi K2.5: 75.3 (#64), Qwen3 8B: —
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1431 | — |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Qwen3 8B: 37.9 (#210)
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | 86.1% | 62.1% |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |
| LMArena Longer Query | 1445 | — |
Writing & Preference Not comparable
Kimi K2.5: 65.1 (#53), Qwen3 8B: —
| Benchmark | Kimi K2.5 | Qwen3 8B |
|---|---|---|
| LMArena Text | 1445 | — |
| LMArena Creative Writing | 1423 | — |
| EQ-Bench Creative Writing | 1579 | — |
| LMArena Multi-Turn | 1444 | — |
Frequently asked questions
Is Kimi K2.5 better than Qwen3 8B?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 33.7 on the Noometry Index. Qwen3 8B costs 2.9× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.5 or Qwen3 8B?
Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Kimi K2.5 or Qwen3 8B better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 131K.
How many benchmarks do Kimi K2.5 and Qwen3 8B share?
8 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen3 8B has 11.