Skip to main content

Model comparison

GPT-OSS 120B vs Qwen3.6-35B-A3B

Data verified

Head-to-head evidence from 17 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

49.97/100
Margin
1.4pts
winning →
51.36/100
0 category wins0 category wins

Verified leaderboard positions: GPT-OSS 120B unranked; Qwen3.6-35B-A3B #31

BenchAlign evidence: GPT-OSS 120B supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-OSS 120B and Qwen3.6-35B-A3B share 17 comparable benchmark results. 0 of 8 categories are comparable. 11 results are unique to GPT-OSS 120B; 41 to Qwen3.6-35B-A3B.

Updated July 15, 2026
Shared results
17
GPT-OSS 120B only
11
Qwen3.6-35B-A3B only
41
Comparable categories
0 / 8

Benchmark data for GPT-OSS 120B and Qwen3.6-35B-A3B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 17 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.

Qwen3.6-35B-A3B has the larger context window at 262K, 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 Qwen3.6-35B-A3B
CategoryGPT-OSS 120BΔQwen3.6-35B-A3B
AgenticGPT-OSS 120BNot measuredMarginNo overlapQwen3.6-35B-A3B51.5
CodingGPT-OSS 120BNot measuredMarginNo overlapQwen3.6-35B-A3B73.8
KnowledgeGPT-OSS 120BNot measuredMarginNo overlapQwen3.6-35B-A3B51.8
MathGPT-OSS 120BNot measuredMarginNo overlapQwen3.6-35B-A3B88.2
MultimodalGPT-OSS 120BNot measuredMarginNo overlapQwen3.6-35B-A3B76.3

Operational comparison

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

MetricGPT-OSS 120BQwen3.6-35B-A3BComparison
Input / output priceUSD per 1M tokensGPT-OSS 120B$0 input / $0 outputQwen3.6-35B-A3BNot availableA complete price comparison is not available.
Generation speedtokens per secondGPT-OSS 120B262 tok/sQwen3.6-35B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-OSS 120B0.79 sQwen3.6-35B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-OSS 120B128KQwen3.6-35B-A3B262KQwen3.6-35B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
AA Agentic IndexSource 13.2%21.4%Qwen3.6-35B-A3B leads
APEX-Agents-AASource 3.1%Not comparable
τ²-bench resultsSource 65.8%95.3%Qwen3.6-35B-A3B leads
GDPval-AASource 15.0%27.4%Qwen3.6-35B-A3B leads
GDPval-AASource 7991049Qwen3.6-35B-A3B leads
Gert LabsSource 29.61%42.65%Qwen3.6-35B-A3B leads
AA EnterpriseOps-GymSource 25.5%Not comparable
AA Harvey LABSource 0.0%Not comparable
AA ITBenchSource 5.6%Not comparable
Terminal-Bench 2.0Source 51.5%Not comparable
Claw-EvalSource 68.7%Not comparable
QwenClawBenchSource 52.6%Not comparable
QwenWebBenchSource 1397Not comparable
τ³-bench resultsSource 67.2%Not comparable
VITA-BenchSource 35.6%Not comparable
DeepPlanningSource 25.9%Not comparable
ToolathlonSource 26.9%Not comparable
MCP AtlasSource 62.8%Not comparable
WideResearchSource 60.1%Not comparable
Coding
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
React Native EvalsSource 71.6%Not comparable
AA Coding IndexSource 30.4%41.9%Qwen3.6-35B-A3B leads
Terminal-Bench HardSource 23.5%34.8%Qwen3.6-35B-A3B leads
AA-SciCodeSource 38.9%35.8%GPT-OSS 120B leads
AA LiveCodeBenchSource 87.8%Not comparable
SWE-bench VerifiedSource 73.4%Not comparable
SWE MultilingualSource 67.2%Not comparable
SWE-bench ProSource 49.5%Not comparable
Terminal-Bench 2.0Source 51.5%Not comparable
LiveCodeBenchSource 80.4%Not comparable
NL2RepoSource 29.4%Not comparable
Reasoning
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
AA-LCRSource 50.7%63.7%Qwen3.6-35B-A3B leads
CritPtSource 1.1%0.3%GPT-OSS 120B leads
Knowledge
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
Artificial Analysis Intelligence IndexSource 23.8%31.6%Qwen3.6-35B-A3B leads
AA-GPQA DiamondSource 78.2%84.1%Qwen3.6-35B-A3B leads
AA-HLESource 18.5%20.2%Qwen3.6-35B-A3B leads
AA-Omniscience IndexSource -50.0%-21.4%Qwen3.6-35B-A3B leads
AA-Omniscience AccuracySource 21.5%18.9%GPT-OSS 120B leads
AA-Omniscience Hallucination RateSource 91.2%49.7%Qwen3.6-35B-A3B leads
AA Openness IndexSource 38.9%Not comparable
AA MMLU-ProSource 80.8%Not comparable
MMLU-ProSource 85.2%Not comparable
SuperGPQASource 64.7%Not comparable
C-EvalSource 90%Not comparable
GPQASource 86%Not comparable
HLESource 21.4%Not comparable
Math
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
AA AIME 2025Source 93.4%Not comparable
HMMT Feb 2025Source 90.7%Not comparable
HMMT Nov 2025Source 89.1%Not comparable
HMMT Feb 2026Source 83.6%Not comparable
MMAnswerBenchSource 78.9%Not comparable
AIME26Source 92.7%Not comparable
Multilingual
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
AA Global-MMLU-LiteSource 82.8%Not comparable
Multimodal
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
Design Arena WebsiteSource 1002Not comparable
MMMUSource 81.7%Not comparable
MMMU-ProSource 75.3%Not comparable
RealWorldQASource 85.3%Not comparable
OmniDocBench 1.5Source 89.9%Not comparable
CharXivSource 78%Not comparable
SimpleVQASource 58.9%Not comparable
CC-OCRSource 81.9%Not comparable
AI2D_TESTSource 92.7%Not comparable
RefCOCO (avg)Source 92.0%Not comparable
ODINW13Source 50.8%Not comparable
Video-MME (with subtitle)Source 86.6%Not comparable
Video-MME (w/o subtitle)Source 82.5%Not comparable
VideoMMMUSource 83.7%Not comparable
MLVU (M-Avg)Source 86.2%Not comparable
AA-MMMU-ProSource 75.0%Not comparable
Inst. Following
BenchmarkGPT-OSS 120BQwen3.6-35B-A3BResult
AA-IFBenchSource 69.0%64.4%GPT-OSS 120B leads
Frequently Asked Questions (3)

Can I compare GPT-OSS 120B and Qwen3.6-35B-A3B 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 Qwen3.6-35B-A3B today?

GPT-OSS 120B: $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.

Related Comparisons

Last updated: July 15, 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.