Model comparison
Kimi K2.5 vs Qwen3-Next 80B-A3B Instruct
Kimi K2.5 is the stronger model overall, scoring 48.1 to 43.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Kimi K2.5 scores higher in 8 categories and Qwen3-Next 80B-A3B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Kimi K2.5 leads 52.1 to 37.0.
- The biggest single-benchmark swing is Fiction.LiveBench: 86.1% for Kimi K2.5 and 55.6% for Qwen3-Next 80B-A3B Instruct.
- Both cost about the same: $0.45 input and $2.25 output per million tokens.
- Kimi K2.5 accepts more context: 262K tokens versus 131K.
Side by side
| Kimi K2.5 | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 48.1 | 43.0 |
| Released | 2026-01-27 | 2025-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 33K |
| Input $ / M tokens | $0.45 | $0.50 |
| Output $ / M tokens | $2.25 | $2 |
| Results tracked | 51 | 25 |
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-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1474 | 1440 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 70.8% | — |
| LMArena WebDev | 1437 | — |
| SWE-bench Multilingual | 67.3% | — |
| SciCode | 49% | — |
| WeirdML | 45.6% | — |
| ALE-Bench | 821.65 | — |
Agentic & Tool Use Not comparable
Kimi K2.5: 34.2 (#48), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Terminal-Bench | 43.2% | — |
| OSWorld | 63.3% | — |
| Vending-Bench 2 | 1,198 | — |
Reasoning Too close to call
Kimi K2.5: 31.2 (#80), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 78.5% | 66.7% |
| LMArena Hard Prompts | 1453 | 1428 |
| ARC-AGI-2 | 11.8% | — |
| SimpleBench | 46.8% | — |
| NYT Connections (extended) | 69.9% | — |
| ARC-AGI-1 | 65.3% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 3.4% | — |
| Thematic Generalization | 69.4% | — |
| Epoch Capabilities Index | 148.03 | — |
Math Kimi K2.5 leads
Kimi K2.5: 51.8 (#53), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1470 | 1440 |
| MathArena Final-Answer Competitions | 62.3% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| Omni-MATH | — | 46.7% |
| FrontierMath (Feb 2025 set) | 27.9% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Kimi K2.5 leads
Kimi K2.5: 53.6 (#56), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Vectara Hallucination Rate | 14.2% | 9.3% |
| LMArena Expert | 1466 | 1417 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 24.4% | — |
| SimpleQA Verified | 34.3% | — |
| MMLU-Pro | — | 78.6% |
| GPQA (HELM) | — | 63% |
Multimodal Not comparable
Kimi K2.5: 41.1 (#39), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Vision | 1269 | — |
| LMArena Document | 1430 | — |
Multilingual Kimi K2.5 leads
Kimi K2.5: 53.9 (#53), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1433 | 1407 |
| LMArena Chinese | 1495 | 1460 |
| LMArena French | 1454 | 1413 |
| LMArena German | 1441 | 1417 |
| LMArena Japanese | 1421 | 1395 |
| LMArena Korean | 1410 | 1364 |
| LMArena Russian | 1435 | 1404 |
| LMArena Spanish | 1450 | 1435 |
Instruction Following Kimi K2.5 leads
Kimi K2.5: 75.3 (#64), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1431 | 1389 |
| IFEval | — | 81% |
Long Context Kimi K2.5 leads
Kimi K2.5: 52.1 (#7), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Fiction.LiveBench | 86.1% | 55.6% |
| LMArena Longer Query | 1445 | 1403 |
| CL-bench | 19.3% | — |
| CL-bench Life | 13.2% | — |
Writing & Preference Kimi K2.5 leads
Kimi K2.5: 65.1 (#53), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | Kimi K2.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1445 | 1417 |
| LMArena Creative Writing | 1423 | 1334 |
| LMArena Multi-Turn | 1444 | 1416 |
| EQ-Bench Creative Writing | 1579 | — |
| WildBench | — | 80.7% |
Frequently asked questions
Is Kimi K2.5 better than Qwen3-Next 80B-A3B Instruct?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 43.0 on the Noometry Index.
Which is cheaper, Kimi K2.5 or Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is cheaper. It lists at $0.50 per million input tokens and $2 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Kimi K2.5 or Qwen3-Next 80B-A3B Instruct better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 42.5 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-Next 80B-A3B Instruct share?
20 benchmarks have published results for both models. Kimi K2.5 has 51 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.