Head to head

Gemma 4 26B A4B vs gpt-oss-120b

gpt-oss-120b scores higher on 3 of the 4 benchmarks both models publish. The widest gap is on AIME, where gpt-oss-120b leads by 7.5 points. Both have open weights; Gemma 4 26B A4B is far lighter to host, needing about 17 GB at 4-bit against 81 GB for gpt-oss-120b.

Gemma 4 26B A4BGoogle · OpenLLM Buddy catalog72.9compositegpt-oss-120bOpenAI · Open weights57.3composite

Shared benchmarks

Raw published scores; the higher score on each row is highlighted. LMArena Elo is a human-preference vote and is not counted as a win.

Should you pick Gemma 4 26B A4B or gpt-oss-120b?

Pick Gemma 4 26B A4B if…

  • You care most about GPQA Diamond, where it scores at least 2 points higher.
  • You want the lighter model to host: about 17 GB at 4-bit against 81 GB.
  • You want to run it locally: at 4-bit it fits one 24–32 GB consumer GPU.
  • You want it running in minutes on a dedicated GPU through OpenLLM Buddy.

Pick gpt-oss-120b if…

  • You care most about Humanity's Last Exam, AIME, where it scores at least 2 points higher.
  • You need fast responses: about 212 tokens per second through APIs, against 113.
  • Cost matters: $0.150 per million output tokens against $0.600.

Hardware and cost to run

Gemma 4 26B A4B

At 4-bit it needs about 17 GB, which fits a single RTX 4090, so it can run on a home workstation with llama.cpp, Ollama, or vLLM. Full BF16 precision needs about 58 GB (1× H100 (80 GB)).

On OpenLLM Buddy: Gemma 4 26B A4B, with an OpenAI-compatible API and no per-token fees. Prices start at $13 USD for 11 Hours.

Deploy Gemma 4 26B A4B
Full GPU memory table for Gemma 4 26B A4B

gpt-oss-120b

Even at 4-bit it needs about 81 GB (1× H200 (141 GB)), well beyond a home workstation, so most people run it on rented multi-GPU servers. Full BF16 precision needs about 269 GB (4× H100 (320 GB)).

Full GPU memory table for gpt-oss-120b

Category profile

Category index uses every test each model reports, not only the shared ones.

ReasoningCodingAgenticKnowledge
Gemma 4 26B A4Bgpt-oss-120b
Reasoning63.268.2
Coding82.576.5
Agentic56.627.1
Knowledge89.3—

Specs side by side

Gemma 4 26B A4Bgpt-oss-120b
LabGoogleOpenAI
WeightsOpenOpen
Released2026-04-022025-08-05
Parameters25.2B total, 3.8B active (MoE)117B total, 5.1B active (MoE)
Context256K128K
LicenseApache-2.0Apache 2.0
4-bit memory17 GB · RTX 4090 (24 GB)81 GB · 1× H200 (141 GB)
API price$0.150 in / $0.600 out per 1M tokens$0.030 in / $0.150 out per 1M tokens
API speed113 tok/s212 tok/s
One-GPU speed (est.)≈ 133–160 tok/s on RTX 4090 (4-bit)—

Related comparisons

Sources

ModelTestScoreSettingSource
Gemma 4 26B A4BGPQA Diamond82.3—Gemma 4 31B IT model card (Hugging Face), 26B A4B column
gpt-oss-120bGPQA Diamond80.1high effort, no toolsgpt-oss model card paper (arXiv 2508.10925), Table 3
Gemma 4 26B A4BHumanity's Last Exam8.7no toolsGemma 4 31B IT model card (Hugging Face), 26B A4B column
gpt-oss-120bHumanity's Last Exam14.9high effort, no toolsgpt-oss model card paper (arXiv 2508.10925), Table 3
Gemma 4 26B A4BHumanity's Last Exam (with tools)17.2with searchGemma 4 31B IT model card (Hugging Face), 26B A4B column
gpt-oss-120bHumanity's Last Exam (with tools)19.0high effort, with toolsgpt-oss model card paper (arXiv 2508.10925), Table 3
Gemma 4 26B A4BAIME88.3AIME 2026, no toolsGemma 4 31B IT model card (Hugging Face), 26B A4B column
gpt-oss-120bAIME95.8AIME 2024, high effort, no toolsgpt-oss model card paper (arXiv 2508.10925), Table 3

Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works