Skip to main content
BenchLM
Advertise

Model comparison

Kimi K2.5 vs Qwen3 235B 2507

Data verified

Head-to-head evidence from 4 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Kimi K2.5
Moonshot AI
59.66/100
Margin
3.6pts
← winning
56.02/100
1 category wins1 category wins

Public leaderboard positions: Kimi K2.5 #54 (Supported); Qwen3 235B 2507 #78 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K2.5 and Qwen3 235B 2507 share 4 comparable benchmark results. 2 of 8 categories are comparable. 59 results are unique to Kimi K2.5; 0 to Qwen3 235B 2507.

Updated July 22, 2026
Shared results
4
Kimi K2.5 only
59
Qwen3 235B 2507 only
0
Comparable categories
2 / 8

Pick Kimi K2.5 if you want the stronger benchmark profile. Qwen3 235B 2507 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 2 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Kimi K2.5 is clearly ahead on the BenchAlign aggregate, 59.66 to 56.02. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K2.5's sharpest advantage is in multilingual, where it averages 82.3 against 79.4. The single biggest benchmark swing on the page is GPQA, 87.6% to 77.5%. Qwen3 235B 2507 does hit back in knowledge, 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 235B 2507. That is roughly Infinityx on output cost alone. Kimi K2.5 gives you the larger context window at 256K, compared with 128K for Qwen3 235B 2507.

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 scores and score margins for Kimi K2.5 and Qwen3 235B 2507
CategoryKimi K2.5ΔQwen3 235B 2507
KnowledgeKimi K2.556.9Margin→ 22.0Qwen3 235B 250778.9
MultilingualKimi K2.582.3Margin← 2.9Qwen3 235B 250779.4
AgenticKimi K2.555.0MarginNo overlapQwen3 235B 2507Not measured
CodingKimi K2.559.4MarginNo overlapQwen3 235B 2507Not measured
ReasoningKimi K2.561.0MarginNo overlapQwen3 235B 2507Not measured
MathKimi K2.560.6MarginNo overlapQwen3 235B 2507Not measured
MultimodalKimi K2.578.5MarginNo overlapQwen3 235B 2507Not measured
Inst. FollowingKimi K2.593.9MarginNo overlapQwen3 235B 2507Not measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Kimi K2.5B · Qwen3 235B 2507

  1. GPQA

    Knowledge
    Source ↗
    A 87.6%B 77.5%
    Winner: Kimi K2.5Δ 10.1
    GPQA: Kimi K2.5 scored 87.6%; Qwen3 235B 2507 scored 77.5%. Kimi K2.5 wins this benchmark.

  2. SuperGPQA

    Knowledge
    Source ↗
    A 69.2%B 62.6%
    Winner: Kimi K2.5Δ 6.6
    SuperGPQA: Kimi K2.5 scored 69.2%; Qwen3 235B 2507 scored 62.6%. Kimi K2.5 wins this benchmark.

  3. MMLU-Pro

    Knowledge
    Source ↗
    A 87.1%B 83%
    Winner: Kimi K2.5Δ 4.1
    MMLU-Pro: Kimi K2.5 scored 87.1%; Qwen3 235B 2507 scored 83%. Kimi K2.5 wins this benchmark.

  4. MMLU-ProX

    Multilingual
    Source ↗
    A 82.3%B 79.4%
    Winner: Kimi K2.5Δ 2.9
    MMLU-ProX: Kimi K2.5 scored 82.3%; Qwen3 235B 2507 scored 79.4%. Kimi K2.5 wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricKimi K2.5Qwen3 235B 2507Comparison
Input / output priceUSD per 1M tokensKimi K2.5$0.6 input / $3 outputQwen3 235B 2507$0 input / $0 outputQwen3 235B 2507 has the lower combined listed price.
Generation speedtokens per secondKimi K2.545 tok/sQwen3 235B 2507Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi K2.52.38 sQwen3 235B 2507Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensKimi K2.5256KQwen3 235B 2507128KKimi K2.5 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkKimi K2.5Qwen3 235B 2507Result
Terminal-Bench 2.0Source 50.8%—Not comparable
BrowseCompSource 60.6%—Not comparable
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%—Not comparable
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%—Not comparable
GDPval-AASource 25.4%—Not comparable
GDPval-AASource 1009—Not comparable
Coding
BenchmarkKimi K2.5Qwen3 235B 2507Result
SWE-bench VerifiedSource 76.8%—Not comparable
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%—Not comparable
AA Coding IndexSource 46.8%—Not comparable
Reasoning
BenchmarkKimi K2.5Qwen3 235B 2507Result
LongBench v2Source 61%—Not comparable
AA-LCRSource 65.3%—Not comparable
CritPtSource 3.1%—Not comparable
KnowledgeQwen3 235B 2507 wins
BenchmarkKimi K2.5Qwen3 235B 2507Result
GPQASource 87.6%77.5%Kimi K2.5 leads
GPQA-DSource 87.6%—Not comparable
SuperGPQASource 69.2%62.6%Kimi K2.5 leads
MMLU-ProSource 87.1%83%Kimi K2.5 leads
MMLU-Pro (Arcee)Source 87.1%—Not comparable
HLESource 30.1%—Not comparable
Artificial Analysis Intelligence IndexSource 35.4%—Not comparable
AA-GPQA DiamondSource 87.9%—Not comparable
AA-HLESource 29.4%—Not comparable
AA-Omniscience IndexSource -8.1%—Not comparable
AA-Omniscience AccuracySource 34.3%—Not comparable
AA-Omniscience Hallucination RateSource 64.6%—Not comparable
Math
BenchmarkKimi K2.5Qwen3 235B 2507Result
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 wins
BenchmarkKimi K2.5Qwen3 235B 2507Result
MMLU-ProXSource 82.3%79.4%Kimi K2.5 leads
NOVA-63Source 56.0%—Not comparable
Multimodal
BenchmarkKimi K2.5Qwen3 235B 2507Result
MMMU-ProSource 78.5%—Not comparable
Video-MMESource 87.4%—Not comparable
MMVUSource 80.4%—Not comparable
VideoMMMUSource 86.6%—Not comparable
AA-MMMU-ProSource 75.4%—Not comparable
Design Arena WebsiteSource 1279—Not comparable
Inst. Following
BenchmarkKimi K2.5Qwen3 235B 2507Result
IFEvalSource 93.9%—Not comparable
AA-IFBenchSource 70.2%—Not comparable
Frequently Asked Questions (3)

Which is better, Kimi K2.5 or Qwen3 235B 2507?

Kimi K2.5 is ahead on BenchLM's BenchAlign leaderboard, 59.66 to 56.02. The biggest single separator in this matchup is GPQA, where the scores are 87.6% and 77.5%.

Which is better for knowledge tasks, Kimi K2.5 or Qwen3 235B 2507?

Qwen3 235B 2507 has the edge for knowledge tasks in this comparison, averaging 78.9 versus 56.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Kimi K2.5 or Qwen3 235B 2507?

Kimi K2.5 has the edge for multilingual tasks in this comparison, averaging 82.3 versus 79.4. 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.

Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Qwen3 235B 2507
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Model the full break-even

Related Comparisons

Explore More

Moonshot AI Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 22, 2026

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.