Model comparison
Kimi K2.5 vs Qwen3.5-122B-A10B
Head-to-head evidence from 26 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Kimi K2.5 #54 (Supported); Qwen3.5-122B-A10B #47 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Kimi K2.5 and Qwen3.5-122B-A10B share 26 comparable benchmark results. 7 of 8 categories are comparable. 37 results are unique to Kimi K2.5; 5 to Qwen3.5-122B-A10B.
Updated July 23, 2026- Shared results
- 26
- Kimi K2.5 only
- 37
- Qwen3.5-122B-A10B only
- 5
- Comparable categories
- 7 / 8
Pick Qwen3.5-122B-A10B if you want the stronger benchmark profile. Kimi K2.5 only becomes the better choice if multimodal & grounded is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 26 shared benchmark results across 7 evidence categories; 7 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Qwen3.5-122B-A10B has the cleaner BenchAlign overall profile here, landing at 60.56 versus 59.66. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Qwen3.5-122B-A10B's sharpest advantage is in knowledge, where it averages 83.6 against 56.9. The single biggest benchmark swing on the page is SWE-bench Verified, 76.8% to 72%. Kimi K2.5 does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Kimi K2.5 is also the more expensive model on tokens at $0.60 input / $3.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-122B-A10B. That is roughly Infinityx on output cost alone. Qwen3.5-122B-A10B is the reasoning model in the pair, while Kimi K2.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Qwen3.5-122B-A10B gives you the larger context window at 262K, compared with 256K for Kimi K2.5.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Kimi K2.5 | Δ | Qwen3.5-122B-A10B |
|---|---|---|---|
| Knowledge | Kimi K2.556.9 | Margin→ 26.7 | Qwen3.5-122B-A10B83.6 |
| Coding | Kimi K2.559.4 | Margin→ 12.6 | Qwen3.5-122B-A10B72.0 |
| Agentic | Kimi K2.555.0 | Margin→ 1.4 | Qwen3.5-122B-A10B56.4 |
| Multimodal | Kimi K2.578.5 | Margin← 1.3 | Qwen3.5-122B-A10B77.2 |
| Reasoning | Kimi K2.561.0 | Margin← 0.8 | Qwen3.5-122B-A10B60.2 |
| Inst. Following | Kimi K2.593.9 | Margin← 0.5 | Qwen3.5-122B-A10B93.4 |
| Multilingual | Kimi K2.582.3 | Margin← 0.1 | Qwen3.5-122B-A10B82.2 |
| Math | Kimi K2.560.6 | MarginNo overlap | Qwen3.5-122B-A10BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 76.8%B 72%Winner: Kimi K2.5Δ 4.8SWE-bench Verified: Kimi K2.5 scored 76.8%; Qwen3.5-122B-A10B scored 72%. Kimi K2.5 wins this benchmark. - Source ↗
BrowseComp
AgenticA 60.6%B 63.8%Winner: Qwen3.5-122B-A10BΔ 3.2BrowseComp: Kimi K2.5 scored 60.6%; Qwen3.5-122B-A10B scored 63.8%. Qwen3.5-122B-A10B wins this benchmark. - Source ↗
SuperGPQA
KnowledgeA 69.2%B 67.1%Winner: Kimi K2.5Δ 2.1SuperGPQA: Kimi K2.5 scored 69.2%; Qwen3.5-122B-A10B scored 67.1%. Kimi K2.5 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 50.8%B 49.4%Winner: Kimi K2.5Δ 1.4Terminal-Bench 2.0: Kimi K2.5 scored 50.8%; Qwen3.5-122B-A10B scored 49.4%. Kimi K2.5 wins this benchmark. - Source ↗
GPQA
KnowledgeA 87.6%B 86.6%Winner: Kimi K2.5Δ 1GPQA: Kimi K2.5 scored 87.6%; Qwen3.5-122B-A10B scored 86.6%. Kimi K2.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Kimi K2.5 | Qwen3.5-122B-A10B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Kimi K2.5$0.6 input / $3 output | Qwen3.5-122B-A10B$0 input / $0 output | Qwen3.5-122B-A10B has the lower combined listed price. |
| Generation speedtokens per second | Kimi K2.545 tok/s | Qwen3.5-122B-A10BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Kimi K2.52.38 s | Qwen3.5-122B-A10BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Kimi K2.5256K | Qwen3.5-122B-A10B262K | Qwen3.5-122B-A10B lists the larger context window. |
Benchmark Deep Dive
AgenticQwen3.5-122B-A10B wins20 benchmarks
| Benchmark | Kimi K2.5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 50.8% | 49.4% | Kimi K2.5 leads |
| BrowseCompSource | 60.6% | 63.8% | Qwen3.5-122B-A10B leads |
| Claw-EvalSource | 52.3% | — | Not comparable |
| QwenClawBenchSource | 54.3% | — | Not comparable |
| τ³-bench resultsSource | 65.7% | — | Not comparable |
| DeepSearchQASource | 77.1% | — | Not comparable |
| DeepPlanningSource | 14.4% | — | Not comparable |
| ToolathlonSource | 27.8% | — | Not comparable |
| MCP AtlasSource | 29.5% | — | Not comparable |
| MCP-TasksSource | 59.1% | — | Not comparable |
| WideResearchSource | 72.7% | — | Not comparable |
| τ²-bench resultsSource | 95.9% | 93.6% | Kimi K2.5 leads |
| APEX-Agents-AASource | 11.5% | — | Not comparable |
| Gert LabsSource | 45.88% | — | Not comparable |
| ResearchClawBenchSource | 14.0% | — | Not comparable |
| JobBenchSource | 8.7% | — | Not comparable |
| AA Agentic IndexSource | 21.7% | 20.7% | Kimi K2.5 leads |
| GDPval-AASource | 25.4% | 23.9% | Kimi K2.5 leads |
| GDPval-AASource | 1009 | 978 | Kimi K2.5 leads |
| OSWorld-VerifiedSource | — | 58% | Not comparable |
CodingQwen3.5-122B-A10B wins10 benchmarks
| Benchmark | Kimi K2.5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 76.8% | 72% | Kimi K2.5 leads |
| SWE-bench Verified*Source | 70.8% | — | Not comparable |
| LiveCodeBench v6Source | 85.0% | — | Not comparable |
| SWE-bench ProSource | 50.7% | — | Not comparable |
| SWE MultilingualSource | 73% | — | Not comparable |
| SWE-RebenchSource | 58.5% | — | Not comparable |
| React Native EvalsSource | 77.2% | — | Not comparable |
| SciCodeSource | 48.7% | — | Not comparable |
| AA-SciCodeSource | 49.0% | 42.0% | Kimi K2.5 leads |
| AA Coding IndexSource | 46.8% | 45.7% | Kimi K2.5 leads |
ReasoningKimi K2.5 wins3 benchmarks
KnowledgeQwen3.5-122B-A10B wins12 benchmarks
| Benchmark | Kimi K2.5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| GPQASource | 87.6% | 86.6% | Kimi K2.5 leads |
| GPQA-DSource | 87.6% | — | Not comparable |
| SuperGPQASource | 69.2% | 67.1% | Kimi K2.5 leads |
| MMLU-ProSource | 87.1% | 86.7% | Kimi K2.5 leads |
| MMLU-Pro (Arcee)Source | 87.1% | — | Not comparable |
| HLESource | 30.1% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 35.4% | 32.3% | Kimi K2.5 leads |
| AA-GPQA DiamondSource | 87.9% | 85.7% | Kimi K2.5 leads |
| AA-HLESource | 29.4% | 23.4% | Kimi K2.5 leads |
| AA-Omniscience IndexSource | -8.1% | -39.6% | Kimi K2.5 leads |
| AA-Omniscience AccuracySource | 34.3% | 24.7% | Kimi K2.5 leads |
| AA-Omniscience Hallucination RateSource | 64.6% | 85.5% | Kimi K2.5 leads |
Math9 benchmarks
| Benchmark | Kimi K2.5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| AIME 2025Source | 96.1% | — | Not comparable |
| AIME26Source | 95.8% | — | Not comparable |
| AIME25 (Arcee)Source | 96.3% | — | Not comparable |
| HMMT Feb 2025Source | 95.4% | — | Not comparable |
| HMMT Nov 2025Source | 91.1% | — | Not comparable |
| HMMT Feb 2026Source | 87.1% | — | Not comparable |
| MMAnswerBenchSource | 81.8% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 27.900% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 4.200% | — | Not comparable |
MultilingualKimi K2.5 wins2 benchmarks
MultimodalKimi K2.5 wins10 benchmarks
| Benchmark | Kimi K2.5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| MMMU-ProSource | 78.5% | — | Not comparable |
| Video-MMESource | 87.4% | — | Not comparable |
| MMVUSource | 80.4% | 74.7% | Kimi K2.5 leads |
| VideoMMMUSource | 86.6% | — | Not comparable |
| AA-MMMU-ProSource | 75.4% | 75.0% | Kimi K2.5 leads |
| Design Arena WebsiteSource | 1279 | — | Not comparable |
| MMMUSource | — | 83.9% | Not comparable |
| MathVisionSource | — | 86.2% | Not comparable |
| CharXivSource | — | 77.2% | Not comparable |
| V*Source | — | 93.2% | Not comparable |
Frequently Asked Questions (8)
Which is better, Kimi K2.5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B is ahead on BenchLM's BenchAlign leaderboard, 60.56 to 59.66. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 76.8% and 72%.
Which is better for knowledge tasks, Kimi K2.5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 83.6 versus 56.9. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Which is better for coding, Kimi K2.5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 72 versus 59.4. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Which is better for reasoning, Kimi K2.5 or Qwen3.5-122B-A10B?
Kimi K2.5 has the edge for reasoning in this comparison, averaging 61 versus 60.2. Inside this category, CritPt is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Kimi K2.5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for agentic tasks in this comparison, averaging 56.4 versus 55. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Kimi K2.5 or Qwen3.5-122B-A10B?
Kimi K2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 78.5 versus 77.2. Inside this category, MMVU is the benchmark that creates the most daylight between them.
Which is better for instruction following, Kimi K2.5 or Qwen3.5-122B-A10B?
Kimi K2.5 has the edge for instruction following in this comparison, averaging 93.9 versus 93.4. Inside this category, AA-IFBench is the benchmark that creates the most daylight between them.
Which is better for multilingual tasks, Kimi K2.5 or Qwen3.5-122B-A10B?
Kimi K2.5 has the edge for multilingual tasks in this comparison, averaging 82.3 versus 82.2. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.