Compare · ModelsLive · 2 picked · head to head
Gemini 3.5 Flash vs Qwen2.5 72B Instruct
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.5 Flash wins on 6/6 benchmarks
Gemini 3.5 Flash wins 6 of 6 shared benchmarks. Leads in arena · general · knowledge.
Category leads
arena·Gemini 3.5 Flashgeneral·Gemini 3.5 Flashknowledge·Gemini 3.5 Flashmath·Gemini 3.5 Flashcoding·Gemini 3.5 Flash
Hype vs Reality
Attention vs performance
Gemini 3.5 Flash
#89 by perf·#10 by attention
Qwen2.5 72B Instruct
#141 by perf·#1 by attention
Best value
Qwen2.5 72B Instruct
12.4x better value than Gemini 3.5 Flash
Gemini 3.5 Flash
10.5 pts/$
$5.25/M
Qwen2.5 72B Instruct
129.7 pts/$
$0.38/M
Vendor risk
Who is behind the model
Google DeepMind
$3.53T·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
6 benchmarks · 2 models
Gemini 3.5 FlashQwen2.5 72B Instruct
Chatbot Arena Elo · Overall
Gemini 3.5 Flash leads by +173.4
Gemini 3.5 Flash
1476.3
Qwen2.5 72B Instruct
1302.8
Dtbench
Gemini 3.5 Flash leads by +52.9
Gemini 3.5 Flash
91.1
Qwen2.5 72B Instruct
38.2
GPQA diamond
Gemini 3.5 Flash leads by +60.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 3.5 Flash
94.2
Qwen2.5 72B Instruct
33.5
Lmca
Gemini 3.5 Flash leads by +39.7
Gemini 3.5 Flash
55.5
Qwen2.5 72B Instruct
15.8
OTIS Mock AIME 2024-2025
Gemini 3.5 Flash leads by +87.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.5 Flash
95.5
Qwen2.5 72B Instruct
8.0
WeirdML
Gemini 3.5 Flash leads by +46.7
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 3.5 Flash
62.6
Qwen2.5 72B Instruct
16.0
Full benchmark table
| Benchmark | Gemini 3.5 Flash | Qwen2.5 72B Instruct |
|---|---|---|
Chatbot Arena Elo · Overall | 1476.3 | 1302.8 |
Dtbench | 91.1 | 38.2 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 94.2 | 33.5 |
Lmca | 55.5 | 15.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 95.5 | 8.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 62.6 | 16.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.50 | $9.00 | 1.0M tokens (~524 books) | $33.75 | |
| $0.36 | $0.40 | 33K tokens (~16 books) | $3.70 |