Beta
Compare · ModelsLive · 2 picked · head to head

Gemma 4 31B vs GPT-5.1-Codex-Mini

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

Gemma 4 31B wins 5 of 8 shared benchmarks. Leads in coding · reasoning · language.

Category leads
coding·Gemma 4 31Breasoning·Gemma 4 31Blanguage·Gemma 4 31Bmath·GPT-5.1-Codex-Miniknowledge·Gemma 4 31B
Hype vs Reality
Gemma 4 31B
#31 by perf·no signal
QUIET
GPT-5.1-Codex-Mini
#39 by perf·no signal
QUIET
Best value
4.5x better value than GPT-5.1-Codex-Mini
Gemma 4 31B
241.6 pts/$
$0.26/M
GPT-5.1-Codex-Mini
53.7 pts/$
$1.13/M
Vendor risk
Google DeepMind logo
Google DeepMind
$4.00T·Tier 1
Low risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
Gemma 4 31BGPT-5.1-Codex-Mini
LiveBench · Agentic Coding
Gemma 4 31B
40.0
GPT-5.1-Codex-Mini
40.0
LiveBench · Coding
GPT-5.1-Codex-Mini leads by +9.6
Gemma 4 31B
60.3
GPT-5.1-Codex-Mini
69.9
LiveBench · Data Analysis
Gemma 4 31B leads by +9.1
Gemma 4 31B
58.8
GPT-5.1-Codex-Mini
49.7
LiveBench · If
Gemma 4 31B leads by +8.6
Gemma 4 31B
67.6
GPT-5.1-Codex-Mini
59.0
LiveBench · Language
Gemma 4 31B leads by +8.3
Gemma 4 31B
71.3
GPT-5.1-Codex-Mini
63.0
LiveBench · Mathematics
GPT-5.1-Codex-Mini leads by +2.3
Gemma 4 31B
73.9
GPT-5.1-Codex-Mini
76.3
LiveBench · Overall
Gemma 4 31B leads by +1.2
Gemma 4 31B
61.6
GPT-5.1-Codex-Mini
60.4
LiveBench · Reasoning
GPT-5.1-Codex-Mini leads by +5.3
Gemma 4 31B
59.4
GPT-5.1-Codex-Mini
64.7
Full benchmark table
BenchmarkGemma 4 31BGPT-5.1-Codex-Mini
LiveBench · Agentic Coding
40.040.0
LiveBench · Coding
60.369.9
LiveBench · Data Analysis
58.849.7
LiveBench · If
67.659.0
LiveBench · Language
71.363.0
LiveBench · Mathematics
73.976.3
LiveBench · Overall
61.660.4
LiveBench · Reasoning
59.464.7
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Google DeepMind logoGemma 4 31B$0.13$0.38262K tokens (~131 books)$1.93
OpenAI logoGPT-5.1-Codex-Mini$0.25$2.00400K tokens (~200 books)$6.88