Skip to main content

Model comparison

Kimi K2.5 (Reasoning) vs Step 3.7 Flash

Data verified

Head-to-head evidence from 22 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

59.06/100
Margin
8.3pts
← winning
50.76/100
1 category wins1 category wins

BenchAlign evidence: Kimi K2.5 (Reasoning) estimated; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K2.5 (Reasoning) and Step 3.7 Flash share 22 comparable benchmark results. 2 of 8 categories are comparable. 6 results are unique to Kimi K2.5 (Reasoning); 8 to Step 3.7 Flash.

Updated July 16, 2026
Shared results
22
Kimi K2.5 (Reasoning) only
6
Step 3.7 Flash only
8
Comparable categories
2 / 8

Pick Kimi K2.5 (Reasoning) if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if agentic is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 22 shared benchmark results across 6 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 (Reasoning) is clearly ahead on the provisional aggregate, 70 to 57. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K2.5 (Reasoning)'s sharpest advantage is in coding, where it averages 76.8 against 56.3. The single biggest benchmark swing on the page is BrowseComp, 60.6% to 75.8%. Step 3.7 Flash does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Kimi K2.5 (Reasoning) is also the more expensive model on tokens at $0.60 input / $3.00 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 2.6x on output cost alone. Step 3.7 Flash gives you the larger context window at 256K, compared with 128K for Kimi K2.5 (Reasoning).

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 (Reasoning) and Step 3.7 Flash
CategoryKimi K2.5 (Reasoning)ΔStep 3.7 Flash
CodingKimi K2.5 (Reasoning)76.8Margin 20.5Step 3.7 Flash56.3
AgenticKimi K2.5 (Reasoning)55.0Margin 11.4Step 3.7 Flash66.4
KnowledgeKimi K2.5 (Reasoning)87.2MarginNo overlapStep 3.7 FlashNot measured
MultimodalKimi K2.5 (Reasoning)78.5MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

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

More
A · Kimi K2.5 (Reasoning)B · Step 3.7 Flash
  1. BrowseComp

    Agentic
    Source ↗
    A 60.6%B 75.8%
    Winner: Step 3.7 FlashΔ 15.2
    BrowseComp: Kimi K2.5 (Reasoning) scored 60.6%; Step 3.7 Flash scored 75.8%. Step 3.7 Flash wins this benchmark.
  2. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 50.8%B 59.5%
    Winner: Step 3.7 FlashΔ 8.7
    Terminal-Bench 2.0: Kimi K2.5 (Reasoning) scored 50.8%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark.

Operational comparison

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

MetricKimi K2.5 (Reasoning)Step 3.7 FlashComparison
Input / output priceUSD per 1M tokensKimi K2.5 (Reasoning)$0.6 input / $3 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondKimi K2.5 (Reasoning)Not availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi K2.5 (Reasoning)Not availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensKimi K2.5 (Reasoning)128KStep 3.7 Flash256KStep 3.7 Flash lists the larger context window.

Benchmark Deep Dive

AgenticStep 3.7 Flash wins
BenchmarkKimi K2.5 (Reasoning)Step 3.7 FlashResult
Terminal-Bench 2.0Source 50.8%59.5%Step 3.7 Flash leads
BrowseCompSource 60.6%75.8%Step 3.7 Flash leads
APEX-Agents-AASource 11.5%14.8%Step 3.7 Flash leads
τ²-bench resultsSource 95.9%98.5%Step 3.7 Flash leads
Gert LabsSource 32.58%51.57%Step 3.7 Flash leads
AA Agentic IndexSource 21.7%21.5%Kimi K2.5 (Reasoning) leads
GDPval-AASource 25.4%25.9%Step 3.7 Flash leads
GDPval-AASource 10091017Step 3.7 Flash leads
DeepSearchQASource 92.8%Not comparable
ToolathlonSource 49.5%Not comparable
Claw-EvalSource 67.1%Not comparable
HLE w/ toolsSource 47.2%Not comparable
CodingKimi K2.5 (Reasoning) wins
BenchmarkKimi K2.5 (Reasoning)Step 3.7 FlashResult
SWE-bench VerifiedSource 76.8%Not comparable
Vibe Code BenchSource 17.54%Not comparable
Terminal-Bench HardSource 34.8%35.6%Step 3.7 Flash leads
AA-SciCodeSource 49.0%40.0%Kimi K2.5 (Reasoning) leads
AA Coding IndexSource 46.8%39.6%Kimi K2.5 (Reasoning) leads
SWE-bench ProSource 56.3%Not comparable
Terminal-Bench 2.0Source 59.5%Not comparable
Reasoning
BenchmarkKimi K2.5 (Reasoning)Step 3.7 FlashResult
AA-LCRSource 65.3%63.7%Kimi K2.5 (Reasoning) leads
CritPtSource 3.1%2.3%Kimi K2.5 (Reasoning) leads
Knowledge
BenchmarkKimi K2.5 (Reasoning)Step 3.7 FlashResult
GPQASource 87.6%Not comparable
MMLU-ProSource 87.1%Not comparable
Artificial Analysis Intelligence IndexSource 35.4%30.3%Kimi K2.5 (Reasoning) leads
AA-GPQA DiamondSource 87.9%80.9%Kimi K2.5 (Reasoning) leads
AA-HLESource 29.4%19.9%Kimi K2.5 (Reasoning) leads
AA-Omniscience IndexSource -8.1%-37.5%Kimi K2.5 (Reasoning) leads
AA-Omniscience AccuracySource 34.3%25.4%Kimi K2.5 (Reasoning) leads
AA-Omniscience Hallucination RateSource 64.6%84.4%Kimi K2.5 (Reasoning) leads
Math
BenchmarkKimi K2.5 (Reasoning)Step 3.7 FlashResult
AIME 2025Source 96.1%Not comparable
Multimodal
BenchmarkKimi K2.5 (Reasoning)Step 3.7 FlashResult
MMMU-ProSource 78.5%Not comparable
AA-MMMU-ProSource 75.4%75.3%Kimi K2.5 (Reasoning) leads
Design Arena WebsiteSource 12841218Kimi K2.5 (Reasoning) leads
SimpleVQASource 79.2%Not comparable
V*Source 95.3%Not comparable
Inst. Following
BenchmarkKimi K2.5 (Reasoning)Step 3.7 FlashResult
AA-IFBenchSource 70.2%67.3%Kimi K2.5 (Reasoning) leads
Frequently Asked Questions (3)

Which is better, Kimi K2.5 (Reasoning) or Step 3.7 Flash?

Kimi K2.5 (Reasoning) is ahead on BenchLM's provisional leaderboard, 70 to 57. The biggest single separator in this matchup is BrowseComp, where the scores are 60.6% and 75.8%.

Which is better for coding, Kimi K2.5 (Reasoning) or Step 3.7 Flash?

Kimi K2.5 (Reasoning) has the edge for coding in this comparison, averaging 76.8 versus 56.3. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Kimi K2.5 (Reasoning) or Step 3.7 Flash?

Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 55. Inside this category, Gert Labs is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 16, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.