Skip to main content
BenchLM
Advertise

Model comparison

GPT-OSS 120B vs Kimi K2.5

Data verified

Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

50.08/100
Margin
9.6pts
winning →
Kimi K2.5
Moonshot AI
59.66/100
0 category wins0 category wins

Public leaderboard positions: GPT-OSS 120B #116 (Supported); Kimi K2.5 #54 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-OSS 120B and Kimi K2.5 share 19 comparable benchmark results. 0 of 8 categories are comparable. 7 results are unique to GPT-OSS 120B; 44 to Kimi K2.5.

Updated July 22, 2026
Shared results
19
GPT-OSS 120B only
7
Kimi K2.5 only
44
Comparable categories
0 / 8

Benchmark data for GPT-OSS 120B and Kimi K2.5 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 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 GPT-OSS 120B. Kimi K2.5 has the larger context window at 256K, compared with 128K for GPT-OSS 120B.

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 GPT-OSS 120B and Kimi K2.5
CategoryGPT-OSS 120BΔKimi K2.5
AgenticGPT-OSS 120BNot measuredMarginNo overlapKimi K2.555.0
CodingGPT-OSS 120BNot measuredMarginNo overlapKimi K2.559.4
ReasoningGPT-OSS 120BNot measuredMarginNo overlapKimi K2.561.0
KnowledgeGPT-OSS 120BNot measuredMarginNo overlapKimi K2.556.9
MathGPT-OSS 120BNot measuredMarginNo overlapKimi K2.560.6
MultilingualGPT-OSS 120BNot measuredMarginNo overlapKimi K2.582.3
MultimodalGPT-OSS 120BNot measuredMarginNo overlapKimi K2.578.5
Inst. FollowingGPT-OSS 120BNot measuredMarginNo overlapKimi K2.593.9

Operational comparison

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

MetricGPT-OSS 120BKimi K2.5Comparison
Input / output priceUSD per 1M tokensGPT-OSS 120B$0 input / $0 outputKimi K2.5$0.6 input / $3 outputGPT-OSS 120B has the lower combined listed price.
Generation speedtokens per secondGPT-OSS 120B262 tok/sKimi K2.545 tok/sGPT-OSS 120B has the higher measured throughput.
First-answer latencyseconds to first tokenGPT-OSS 120B0.79 sKimi K2.52.38 sGPT-OSS 120B reaches the first token sooner.
Context windowmaximum listed tokensGPT-OSS 120B128KKimi K2.5256KKimi K2.5 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGPT-OSS 120BKimi K2.5Result
AA Agentic IndexSource 13.2%21.7%Kimi K2.5 leads
APEX-Agents-AASource 3.1%11.5%Kimi K2.5 leads
τ²-bench resultsSource 65.8%95.9%Kimi K2.5 leads
GDPval-AASource 15.0%25.4%Kimi K2.5 leads
GDPval-AASource 7991009Kimi K2.5 leads
Gert LabsSource 29.61%45.88%Kimi K2.5 leads
AA EnterpriseOps-GymSource 25.5%—Not comparable
AA ITBenchSource 5.6%—Not comparable
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
ResearchClawBenchSource —14.0%Not comparable
JobBenchSource —8.7%Not comparable
Coding
BenchmarkGPT-OSS 120BKimi K2.5Result
React Native EvalsSource 71.6%77.2%Kimi K2.5 leads
AA Coding IndexSource 30.4%46.8%Kimi K2.5 leads
AA-SciCodeSource 38.9%49.0%Kimi K2.5 leads
AA LiveCodeBenchSource 87.8%—Not comparable
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
SciCodeSource —48.7%Not comparable
Reasoning
BenchmarkGPT-OSS 120BKimi K2.5Result
AA-LCRSource 50.7%65.3%Kimi K2.5 leads
CritPtSource 1.1%3.1%Kimi K2.5 leads
LongBench v2Source —61%Not comparable
Knowledge
BenchmarkGPT-OSS 120BKimi K2.5Result
Artificial Analysis Intelligence IndexSource 23.8%35.4%Kimi K2.5 leads
AA-GPQA DiamondSource 78.2%87.9%Kimi K2.5 leads
AA-HLESource 18.5%29.4%Kimi K2.5 leads
AA-Omniscience IndexSource -50.0%-8.1%Kimi K2.5 leads
AA-Omniscience AccuracySource 21.5%34.3%Kimi K2.5 leads
AA-Omniscience Hallucination RateSource 91.2%64.6%Kimi K2.5 leads
AA Openness IndexSource 38.9%—Not comparable
AA MMLU-ProSource 80.8%—Not comparable
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
Math
BenchmarkGPT-OSS 120BKimi K2.5Result
AA AIME 2025Source 93.4%—Not comparable
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
BenchmarkGPT-OSS 120BKimi K2.5Result
AA Global-MMLU-LiteSource 82.8%—Not comparable
MMLU-ProXSource —82.3%Not comparable
NOVA-63Source —56.0%Not comparable
Multimodal
BenchmarkGPT-OSS 120BKimi K2.5Result
Design Arena WebsiteSource 9981279Kimi K2.5 leads
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
Inst. Following
BenchmarkGPT-OSS 120BKimi K2.5Result
AA-IFBenchSource 69.0%70.2%Kimi K2.5 leads
IFEvalSource —93.9%Not comparable
Frequently Asked Questions (3)

Can I compare GPT-OSS 120B and Kimi K2.5 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 GPT-OSS 120B and Kimi K2.5 today?

GPT-OSS 120B: $0.00 input / $0.00 output per 1M tokens Kimi K2.5: $0.60 input / $3.00 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.

GPT-OSS 120B
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Model the full break-even

Related Comparisons

Explore More

OpenAI 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.