Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs GPT-OSS 120B

Data verified

Head-to-head evidence from 14 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

65.07/100
Margin
15.0pts
← winning
50.08/100
0 category wins0 category wins

Public leaderboard positions: Claude Sonnet 4.6 #32 (Supported); GPT-OSS 120B #116 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Sonnet 4.6 and GPT-OSS 120B share 14 comparable benchmark results. 0 of 8 categories are comparable. 19 results are unique to Claude Sonnet 4.6; 13 to GPT-OSS 120B.

Updated July 20, 2026
Shared results
14
Claude Sonnet 4.6 only
19
GPT-OSS 120B only
13
Comparable categories
0 / 8

Benchmark data for Claude Sonnet 4.6 and GPT-OSS 120B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 14 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.

Claude Sonnet 4.6 is priced at $3.00 input / $15.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for GPT-OSS 120B. Claude Sonnet 4.6 has the larger context window at 200K, 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 Claude Sonnet 4.6 and GPT-OSS 120B
CategoryClaude Sonnet 4.6ΔGPT-OSS 120B
AgenticClaude Sonnet 4.665.2MarginNo overlapGPT-OSS 120BNot measured
CodingClaude Sonnet 4.669.1MarginNo overlapGPT-OSS 120BNot measured
KnowledgeClaude Sonnet 4.666.0MarginNo overlapGPT-OSS 120BNot measured
MathClaude Sonnet 4.626.4MarginNo overlapGPT-OSS 120BNot measured
MultimodalClaude Sonnet 4.677.4MarginNo overlapGPT-OSS 120BNot measured

Operational comparison

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

MetricClaude Sonnet 4.6GPT-OSS 120BComparison
Input / output priceUSD per 1M tokensClaude Sonnet 4.6$3 input / $15 outputGPT-OSS 120B$0 input / $0 outputGPT-OSS 120B has the lower combined listed price.
Generation speedtokens per secondClaude Sonnet 4.644 tok/sGPT-OSS 120B262 tok/sGPT-OSS 120B has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Sonnet 4.61.48 sGPT-OSS 120B0.79 sGPT-OSS 120B reaches the first token sooner.
Context windowmaximum listed tokensClaude Sonnet 4.6200KGPT-OSS 120B128KClaude Sonnet 4.6 lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
Terminal-Bench 2.0Source 59.1%—Not comparable
OSWorld-VerifiedSource 72.1%—Not comparable
Claw-EvalSource 67.8%—Not comparable
CyberGymSource 65.2%—Not comparable
τ²-bench resultsSource 79.5%65.8%Claude Sonnet 4.6 leads
Gert LabsSource 62.92%29.61%Claude Sonnet 4.6 leads
OSWorld 2.0Source 8.3%—Not comparable
JobBenchSource 36.9%—Not comparable
AA Agentic IndexSource —13.2%Not comparable
APEX-Agents-AASource —3.1%Not comparable
GDPval-AASource —15.0%Not comparable
GDPval-AASource —799Not comparable
AA EnterpriseOps-GymSource —25.5%Not comparable
AA Harvey LABSource —0.0%Not comparable
AA ITBenchSource —5.6%Not comparable
Coding
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
SWE-bench VerifiedSource 79.6%—Not comparable
SWE-RebenchSource 60.7%—Not comparable
React Native EvalsSource 80.6%71.6%Claude Sonnet 4.6 leads
Vibe Code BenchSource 51.48%—Not comparable
cursorBench31Source 48.8%—Not comparable
AA-SciCodeSource 46.9%38.9%Claude Sonnet 4.6 leads
FrontierCode 1.1 MainSource 24.3%—Not comparable
AA Coding IndexSource —30.4%Not comparable
AA LiveCodeBenchSource —87.8%Not comparable
Reasoning
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
AA-LCRSource 57.7%50.7%Claude Sonnet 4.6 leads
CritPtSource 0.9%1.1%GPT-OSS 120B leads
Knowledge
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
GPQASource 89.9%—Not comparable
SuperGPQASource 95%—Not comparable
MMLU-ProSource 79.2%—Not comparable
HLESource 49%—Not comparable
Artificial Analysis Intelligence IndexSource 35.9%23.8%Claude Sonnet 4.6 leads
AA-GPQA DiamondSource 79.9%78.2%Claude Sonnet 4.6 leads
AA-HLESource 13.2%18.5%GPT-OSS 120B leads
AA-Omniscience IndexSource -2.9%-50.0%Claude Sonnet 4.6 leads
AA-Omniscience AccuracySource 38.0%21.5%Claude Sonnet 4.6 leads
AA-Omniscience Hallucination RateSource 65.9%91.2%Claude Sonnet 4.6 leads
AA Openness IndexSource —38.9%Not comparable
AA MMLU-ProSource —80.8%Not comparable
Math
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
FrontierMath v2 (Tiers 1-3)Source 32.400%—Not comparable
FrontierMath v2 (Tier 4)Source 8.300%—Not comparable
AA AIME 2025Source —93.4%Not comparable
Multilingual
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
AA Global-MMLU-LiteSource —82.8%Not comparable
Multimodal
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
CharXivSource 77.4%—Not comparable
AA-MMMU-ProSource 70.6%—Not comparable
Design Arena WebsiteSource 13171000Claude Sonnet 4.6 leads
Inst. Following
BenchmarkClaude Sonnet 4.6GPT-OSS 120BResult
AA-IFBenchSource 41.2%69.0%GPT-OSS 120B leads
Frequently Asked Questions (3)

Can I compare Claude Sonnet 4.6 and GPT-OSS 120B 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 Claude Sonnet 4.6 and GPT-OSS 120B today?

Claude Sonnet 4.6: $3.00 input / $15.00 output per 1M tokens 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

Explore More

Anthropic 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.