Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 5 vs Gemma 4 31B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 5 wins on 8/8 benchmarks
Claude Sonnet 5 wins 8 of 8 shared benchmarks. Leads in knowledge · general · math.
Category leads
knowledge·Claude Sonnet 5general·Claude Sonnet 5math·Claude Sonnet 5coding·Claude Sonnet 5
Hype vs Reality
Attention vs performance
Claude Sonnet 5
#66 by perf·#10 by attention
Gemma 4 31B
#101 by perf·#7 by attention
Best value
Gemma 4 31B
26.0x better value than Claude Sonnet 5
Claude Sonnet 5
9.5 pts/$
$6.00/M
Gemma 4 31B
245.6 pts/$
$0.22/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Google DeepMind
$4.20T·Tier 1
Head to head
8 benchmarks · 2 models
Claude Sonnet 5Gemma 4 31B
Chess Puzzles
Claude Sonnet 5 leads by +31.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Sonnet 5
31.6
Gemma 4 31B
0.0
Dtbench
Claude Sonnet 5 leads by +16.3
Claude Sonnet 5
87.5
Gemma 4 31B
71.1
GPQA diamond
Claude Sonnet 5 leads by +19.7
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 5
87.4
Gemma 4 31B
67.7
Lmca
Claude Sonnet 5 leads by +12.7
Claude Sonnet 5
58.9
Gemma 4 31B
46.2
OTIS Mock AIME 2024-2025
Claude Sonnet 5 leads by +21.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 5
94.7
Gemma 4 31B
73.3
SimpleQA Verified
Claude Sonnet 5 leads by +23.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Sonnet 5
33.7
Gemma 4 31B
10.4
Surface Evolver Bench
Claude Sonnet 5 leads by +29.4
Claude Sonnet 5
60.0
Gemma 4 31B
30.6
WeirdML
Claude Sonnet 5 leads by +16.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 5
68.8
Gemma 4 31B
52.3
Full benchmark table
| Benchmark | Claude Sonnet 5 | Gemma 4 31B |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 31.6 | 0.0 |
Dtbench | 87.5 | 71.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.4 | 67.7 |
Lmca | 58.9 | 46.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.7 | 73.3 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 33.7 | 10.4 |
Surface Evolver Bench | 60.0 | 30.6 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 68.8 | 52.3 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $10.00 | 1.0M tokens (~500 books) | $40.00 | |
| $0.09 | $0.34 | 262K tokens (~131 books) | $1.53 |