Compare · ModelsLive · 2 picked · head to head
Gemini 3.8 Flash vs Qwen3.5 397B A17B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.8 Flash wins on 16/16 benchmarks
Gemini 3.8 Flash wins 16 of 16 shared benchmarks. Leads in speed · agentic · knowledge.
Category leads
speed·Gemini 3.8 Flashagentic·Gemini 3.8 Flashknowledge·Gemini 3.8 Flashgeneral·Gemini 3.8 Flashmath·Gemini 3.8 Flash
Hype vs Reality
Attention vs performance
Gemini 3.8 Flash
#53 by perf·#3 by attention
Qwen3.5 397B A17B
#51 by perf·#2 by attention
Best value
Qwen3.5 397B A17B
1.1x better value than Gemini 3.8 Flash
Gemini 3.8 Flash
26.5 pts/$
$2.25/M
Qwen3.5 397B A17B
29.6 pts/$
$2.02/M
Vendor risk
Who is behind the model
Google DeepMind
$4.25T·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
16 benchmarks · 2 models
Gemini 3.8 FlashQwen3.5 397B A17B
Artificial Analysis · CritPt
Gemini 3.8 Flash leads by +17.4
Gemini 3.8 Flash
18.3
Qwen3.5 397B A17B
0.9
Artificial Analysis · GDPval
Gemini 3.8 Flash leads by +32.2
Gemini 3.8 Flash
46.8
Qwen3.5 397B A17B
14.6
Artificial Analysis · GPQA Diamond
Gemini 3.8 Flash leads by +9.2
Gemini 3.8 Flash
95.3
Qwen3.5 397B A17B
86.1
Artificial Analysis · Humanity's Last Exam
Gemini 3.8 Flash leads by +28.0
Gemini 3.8 Flash
47.8
Qwen3.5 397B A17B
19.8
Artificial Analysis · Long Context Reasoning
Gemini 3.8 Flash leads by +17.0
Gemini 3.8 Flash
81.3
Qwen3.5 397B A17B
64.3
Artificial Analysis · MMMU Pro
Gemini 3.8 Flash leads by +32.9
Gemini 3.8 Flash
85.6
Qwen3.5 397B A17B
52.7
Artificial Analysis · Quality Index
Gemini 3.8 Flash leads by +19.5
Gemini 3.8 Flash
40.9
Qwen3.5 397B A17B
21.4
Artificial Analysis · SciCode
Gemini 3.8 Flash leads by +11.8
Gemini 3.8 Flash
56.6
Qwen3.5 397B A17B
44.8
APEX-Agents
Gemini 3.8 Flash leads by +39.4
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Gemini 3.8 Flash
64.3
Qwen3.5 397B A17B
24.9
Chess Puzzles
Gemini 3.8 Flash leads by +47.4
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemini 3.8 Flash
55.8
Qwen3.5 397B A17B
8.5
Dtbench
Gemini 3.8 Flash leads by +13.8
Gemini 3.8 Flash
92.9
Qwen3.5 397B A17B
79.1
FrontierMath-Tiers-1-3-v2-Private
Gemini 3.8 Flash leads by +37.2
Gemini 3.8 Flash
68.4
Qwen3.5 397B A17B
31.2
GPQA diamond
Gemini 3.8 Flash leads by +12.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 3.8 Flash
93.9
Qwen3.5 397B A17B
81.8
Lmca
Gemini 3.8 Flash leads by +17.7
Gemini 3.8 Flash
62.2
Qwen3.5 397B A17B
44.6
Mystery Game Puzzles
Gemini 3.8 Flash leads by +31.9
Gemini 3.8 Flash
41.6
Qwen3.5 397B A17B
9.7
OTIS Mock AIME 2024-2025
Gemini 3.8 Flash leads by +10.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.8 Flash
98.9
Qwen3.5 397B A17B
88.9
Full benchmark table
| Benchmark | Gemini 3.8 Flash | Qwen3.5 397B A17B |
|---|---|---|
Artificial Analysis · CritPt | 18.3 | 0.9 |
Artificial Analysis · GDPval | 46.8 | 14.6 |
Artificial Analysis · GPQA Diamond | 95.3 | 86.1 |
Artificial Analysis · Humanity's Last Exam | 47.8 | 19.8 |
Artificial Analysis · Long Context Reasoning | 81.3 | 64.3 |
Artificial Analysis · MMMU Pro | 85.6 | 52.7 |
Artificial Analysis · Quality Index | 40.9 | 21.4 |
Artificial Analysis · SciCode | 56.6 | 44.8 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 64.3 | 24.9 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 55.8 | 8.5 |
Dtbench | 92.9 | 79.1 |
FrontierMath-Tiers-1-3-v2-Private | 68.4 | 31.2 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 93.9 | 81.8 |
Lmca | 62.2 | 44.6 |
Mystery Game Puzzles | 41.6 | 9.7 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.9 | 88.9 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.75 | $3.75 | 1.0M tokens (~524 books) | $15.00 | |
| $0.55 | $3.50 | 262K tokens (~131 books) | $12.88 |
People also compared
Gemini 3.8 Flash vs Gemini 4 ArgonQwen3 30B A3B Thinking 2507 vs Qwen3.5 397B A17BGemini 2.0 Flash Lite vs Gemini 3.8 FlashQwen3.5 397B A17B vs Qwen3.7 MaxQwen3.5 397B A17B vs Qwen3 Next 80B A3B ThinkingQwen-14B vs Qwen3.5 397B A17BGemini 3.7 Flash vs Gemini 3.8 FlashGemini 3.8 Flash vs Gemini 3 Pro