token.app › Compare › R1 vs Gemma 4 31B

R1 vs Gemma 4 31B

Gemma 4 31B leads on 2 of 2 shared benchmarks. Gemma 4 31B is 7.2× cheaper per token on a blended 3:1 basis. Gemma 4 31B accepts the larger context window (262K).

Head to head
Blended price uses a 3:1 input:output mix
R1Gemma 4 31B
ProviderDeepSeekGoogle
Input $/1M$0.700$0.100
Output $/1M$2.50$0.340
Blended $/1M$1.15$0.160
Context window164K262K
Max output16K262K
ReleasedJan 2025Apr 2026
LicenceOpen weightsOpen weights
GPQA Diamond 71.7% 75.8%
OTIS Mock AIME 53.3% 73.3%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose R1 if…
  • No clear advantage on the data we hold.
Choose Gemma 4 31B if…
  • Costs less per token — $0.160 vs $1.15 blended
  • Higher GPQA Diamond (75.8% vs 71.7%)
  • Higher OTIS Mock AIME (73.3% vs 53.3%)
  • Larger context window (262K)
  • Newer model (released Apr 2026)
FAQ
Which is better, R1 or Gemma 4 31B?
Across the 2 benchmarks both models have independently-run scores for, R1 leads on 0 and Gemma 4 31B leads on 2. Benchmarks are one input — price and context window are on this page too.
Is R1 cheaper than Gemma 4 31B?
Gemma 4 31B is cheaper: $0.160 versus $1.15 per million tokens blended at 3:1 input:output. Input alone: $0.700 vs $0.100. Output alone: $2.50 vs $0.340.
What context windows do R1 and Gemma 4 31B have?
R1: 163,840 tokens. Gemma 4 31B: 262,144 tokens.
Who makes R1 and Gemma 4 31B?
R1 is made by DeepSeek. Gemma 4 31B is made by Google.
Related comparisons