Skip to main content
BenchLM
Advertise

Model comparison

Kimi K2.5 vs Llama 3.1 405B

Data verified

Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Kimi K2.5
Moonshot AI
59.66/100
Margin
7.9pts
← winning
51.71/100
0 category wins0 category wins

Public leaderboard positions: Kimi K2.5 #54 (Supported); Llama 3.1 405B #102 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Kimi K2.5 and Llama 3.1 405B share 11 comparable benchmark results. 0 of 8 categories are comparable. 52 results are unique to Kimi K2.5; 0 to Llama 3.1 405B.

Updated July 20, 2026
Shared results
11
Kimi K2.5 only
52
Llama 3.1 405B only
0
Comparable categories
0 / 8

Benchmark data for Kimi K2.5 and Llama 3.1 405B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Kimi K2.5 is priced at $0.60 input / $3.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Llama 3.1 405B. Kimi K2.5 has the larger context window at 256K, compared with 128K for Llama 3.1 405B.

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 Llama 3.1 405B
CategoryKimi K2.5ΔLlama 3.1 405B
AgenticKimi K2.555.0MarginNo overlapLlama 3.1 405BNot measured
CodingKimi K2.559.4MarginNo overlapLlama 3.1 405BNot measured
ReasoningKimi K2.561.0MarginNo overlapLlama 3.1 405BNot measured
KnowledgeKimi K2.556.9MarginNo overlapLlama 3.1 405BNot measured
MathKimi K2.560.6MarginNo overlapLlama 3.1 405BNot measured
MultilingualKimi K2.582.3MarginNo overlapLlama 3.1 405BNot measured
MultimodalKimi K2.578.5MarginNo overlapLlama 3.1 405BNot measured
Inst. FollowingKimi K2.593.9MarginNo overlapLlama 3.1 405BNot measured

Operational comparison

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

MetricKimi K2.5Llama 3.1 405BComparison
Input / output priceUSD per 1M tokensKimi K2.5$0.6 input / $3 outputLlama 3.1 405B$0 input / $0 outputLlama 3.1 405B has the lower combined listed price.
Generation speedtokens per secondKimi K2.545 tok/sLlama 3.1 405B29 tok/sKimi K2.5 has the higher measured throughput.
First-answer latencyseconds to first tokenKimi K2.52.38 sLlama 3.1 405B2.19 sLlama 3.1 405B reaches the first token sooner.
Context windowmaximum listed tokensKimi K2.5256KLlama 3.1 405B128KKimi K2.5 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkKimi K2.5Llama 3.1 405BResult
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%19%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%—Not comparable
GDPval-AASource 25.4%—Not comparable
GDPval-AASource 1009—Not comparable
Coding
BenchmarkKimi K2.5Llama 3.1 405BResult
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%29.9%Kimi K2.5 leads
AA Coding IndexSource 46.8%—Not comparable
Reasoning
BenchmarkKimi K2.5Llama 3.1 405BResult
LongBench v2Source 61%—Not comparable
AA-LCRSource 65.3%24.3%Kimi K2.5 leads
CritPtSource 3.1%0.0%Kimi K2.5 leads
Knowledge
BenchmarkKimi K2.5Llama 3.1 405BResult
GPQASource 87.6%—Not comparable
GPQA-DSource 87.6%—Not comparable
SuperGPQASource 69.2%—Not comparable
MMLU-ProSource 87.1%—Not comparable
MMLU-Pro (Arcee)Source 87.1%—Not comparable
HLESource 30.1%—Not comparable
Artificial Analysis Intelligence IndexSource 35.4%8.5%Kimi K2.5 leads
AA-GPQA DiamondSource 87.9%51.5%Kimi K2.5 leads
AA-HLESource 29.4%4.2%Kimi K2.5 leads
AA-Omniscience IndexSource -8.1%-17.3%Kimi K2.5 leads
AA-Omniscience AccuracySource 34.3%22.3%Kimi K2.5 leads
AA-Omniscience Hallucination RateSource 64.6%51.0%Llama 3.1 405B leads
Math
BenchmarkKimi K2.5Llama 3.1 405BResult
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
Multilingual
BenchmarkKimi K2.5Llama 3.1 405BResult
MMLU-ProXSource 82.3%—Not comparable
NOVA-63Source 56.0%—Not comparable
Multimodal
BenchmarkKimi K2.5Llama 3.1 405BResult
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 1282—Not comparable
Inst. Following
BenchmarkKimi K2.5Llama 3.1 405BResult
IFEvalSource 93.9%—Not comparable
AA-IFBenchSource 70.2%39.0%Kimi K2.5 leads
Frequently Asked Questions (3)

Can I compare Kimi K2.5 and Llama 3.1 405B on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Kimi K2.5 and Llama 3.1 405B today?

Kimi K2.5: $0.60 input / $3.00 output per 1M tokens Llama 3.1 405B: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

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
Llama 3.1 405B
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 20, 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.