Compare · ModelsLive · 2 picked · head to head

Qwen3 235B A22B vs Gemma 2 27B

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

Winner summary

Qwen3 235B A22B wins 3 of 3 shared benchmarks. Leads in arena · knowledge · math.

Category leads
arena·Qwen3 235B A22Bknowledge·Qwen3 235B A22Bmath·Qwen3 235B A22B
Hype vs Reality
Qwen3 235B A22B
#60 by perf·no signal
QUIET
Gemma 2 27B
#177 by perf·no signal
QUIET
Best value
1.0x better value than Qwen3 235B A22B
Qwen3 235B A22B
49.6 pts/$
$1.14/M
Gemma 2 27B
50.6 pts/$
$0.65/M
Vendor risk
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Google DeepMind logo
Google DeepMind
$4.00T·Tier 1
Low risk
Head to head
Qwen3 235B A22BGemma 2 27B
Chatbot Arena Elo · Overall
Qwen3 235B A22B leads by +86.9
Qwen3 235B A22B
1374.4
Gemma 2 27B
1287.6
GPQA diamond
Qwen3 235B A22B leads by +45.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen3 235B A22B
60.9
Gemma 2 27B
15.3
MATH level 5
Qwen3 235B A22B leads by +41.0
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Qwen3 235B A22B
68.9
Gemma 2 27B
27.9
Full benchmark table
BenchmarkQwen3 235B A22BGemma 2 27B
Chatbot Arena Elo · Overall
1374.41287.6
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
60.915.3
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
68.927.9
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Alibaba Qwen logoQwen3 235B A22B$0.46$1.82131K tokens (~66 books)$7.96
Google DeepMind logoGemma 2 27B$0.65$0.658K tokens (~4 books)$6.50
People also compared