Skip to main content

Model comparison

Gemma 3 27B vs GPT-OSS 120B

Data verified

Head-to-head evidence from 15 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

41.57/100
Margin
8.5pts
winning →
50.08/100
0 category wins0 category wins

Public leaderboard positions: Gemma 3 27B #164 (Supported); GPT-OSS 120B #116 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 3 27B and GPT-OSS 120B share 15 comparable benchmark results. 0 of 8 categories are comparable. 1 result is unique to Gemma 3 27B; 11 to GPT-OSS 120B.

Updated July 22, 2026
Shared results
15
Gemma 3 27B only
1
GPT-OSS 120B only
11
Comparable categories
0 / 8

Benchmark data for Gemma 3 27B and GPT-OSS 120B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 15 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.

GPT-OSS 120B has the larger context window at 128K, compared with 32K for Gemma 3 27B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Operational comparison

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

MetricGemma 3 27BGPT-OSS 120BComparison
Input / output priceUSD per 1M tokensGemma 3 27B$0 input / $0 outputGPT-OSS 120B$0 input / $0 outputListed prices are equal.
Generation speedtokens per secondGemma 3 27B31 tok/sGPT-OSS 120B262 tok/sGPT-OSS 120B has the higher measured throughput.
First-answer latencyseconds to first tokenGemma 3 27B2.04 sGPT-OSS 120B0.79 sGPT-OSS 120B reaches the first token sooner.
Context windowmaximum listed tokensGemma 3 27B32KGPT-OSS 120B128KGPT-OSS 120B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemma 3 27BGPT-OSS 120BResult
AA Agentic IndexSource 0.3%13.2%GPT-OSS 120B leads
τ²-bench resultsSource 10.5%65.8%GPT-OSS 120B leads
GDPval-AASource 0.0%15.0%GPT-OSS 120B leads
GDPval-AASource -144799GPT-OSS 120B leads
APEX-Agents-AASource 3.1%Not comparable
Gert LabsSource 29.61%Not comparable
AA EnterpriseOps-GymSource 25.5%Not comparable
AA ITBenchSource 5.6%Not comparable
Coding
BenchmarkGemma 3 27BGPT-OSS 120BResult
AA Coding IndexSource 10.1%30.4%GPT-OSS 120B leads
AA-SciCodeSource 21.2%38.9%GPT-OSS 120B leads
React Native EvalsSource 71.6%Not comparable
AA LiveCodeBenchSource 87.8%Not comparable
Reasoning
BenchmarkGemma 3 27BGPT-OSS 120BResult
AA-LCRSource 5.7%50.7%GPT-OSS 120B leads
CritPtSource 0.0%1.1%GPT-OSS 120B leads
Knowledge
BenchmarkGemma 3 27BGPT-OSS 120BResult
Artificial Analysis Intelligence IndexSource 7.4%23.8%GPT-OSS 120B leads
AA-GPQA DiamondSource 42.8%78.2%GPT-OSS 120B leads
AA-HLESource 4.7%18.5%GPT-OSS 120B leads
AA-Omniscience IndexSource -65.9%-50.0%GPT-OSS 120B leads
AA-Omniscience AccuracySource 12.5%21.5%GPT-OSS 120B leads
AA-Omniscience Hallucination RateSource 89.5%91.2%Gemma 3 27B leads
AA Openness IndexSource 38.9%Not comparable
AA MMLU-ProSource 80.8%Not comparable
Math
BenchmarkGemma 3 27BGPT-OSS 120BResult
AA AIME 2025Source 93.4%Not comparable
Multilingual
BenchmarkGemma 3 27BGPT-OSS 120BResult
AA Global-MMLU-LiteSource 82.8%Not comparable
Multimodal
BenchmarkGemma 3 27BGPT-OSS 120BResult
AA-MMMU-ProSource 48.0%Not comparable
Design Arena WebsiteSource 998Not comparable
Inst. Following
BenchmarkGemma 3 27BGPT-OSS 120BResult
AA-IFBenchSource 31.8%69.0%GPT-OSS 120B leads
Frequently Asked Questions (3)

Can I compare Gemma 3 27B 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 Gemma 3 27B and GPT-OSS 120B today?

Gemma 3 27B: $0.00 input / $0.00 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

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.