Compare · ModelsLive · 2 picked · head to head
Gemini 3.5 Flash vs Gemini 3.8 Flash
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.8 Flash wins on 12/14 benchmarks
Gemini 3.8 Flash wins 12 of 14 shared benchmarks. Leads in agentic · knowledge · coding.
Category leads
speed·Gemini 3.5 Flashagentic·Gemini 3.8 Flashknowledge·Gemini 3.8 Flashcoding·Gemini 3.8 Flashgeneral·Gemini 3.8 Flashmath·Gemini 3.8 Flash
Hype vs Reality
Attention vs performance
Gemini 3.5 Flash
#82 by perf·#8 by attention
Gemini 3.8 Flash
#63 by perf·#8 by attention
Best value
Gemini 3.8 Flash
2.4x better value than Gemini 3.5 Flash
Gemini 3.5 Flash
10.4 pts/$
$5.25/M
Gemini 3.8 Flash
25.5 pts/$
$2.25/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
Google DeepMind
$4.20T·Tier 1
Head to head
14 benchmarks · 2 models
Gemini 3.5 FlashGemini 3.8 Flash
Artificial Analysis · Quality Index
Gemini 3.5 Flash leads by +9.3
Gemini 3.5 Flash
50.2
Gemini 3.8 Flash
40.9
APEX-Agents
Gemini 3.8 Flash leads by +36.8
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Gemini 3.5 Flash
27.5
Gemini 3.8 Flash
64.3
Chess Puzzles
Gemini 3.8 Flash leads by +11.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemini 3.5 Flash
47.4
Gemini 3.8 Flash
59.0
Deepswe
Gemini 3.8 Flash leads by +36.4
Gemini 3.5 Flash
37.4
Gemini 3.8 Flash
73.8
Dtbench
Gemini 3.8 Flash leads by +1.8
Gemini 3.5 Flash
91.1
Gemini 3.8 Flash
92.9
FrontierMath-Tier-4-v2-Private
Gemini 3.5 Flash leads by +4.9
Gemini 3.5 Flash
26.8
Gemini 3.8 Flash
21.9
FrontierMath-Tiers-1-3-v2-Private
Gemini 3.8 Flash leads by +5.6
Gemini 3.5 Flash
62.8
Gemini 3.8 Flash
68.4
GPQA diamond
Gemini 3.8 Flash leads by +3.5
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
90.4
Gemini 3.8 Flash
93.9
Lmca
Gemini 3.8 Flash leads by +6.8
Gemini 3.5 Flash
55.5
Gemini 3.8 Flash
62.2
Mystery Game Puzzles
Gemini 3.8 Flash leads by +16.5
Gemini 3.5 Flash
25.1
Gemini 3.8 Flash
41.6
OTIS Mock AIME 2024-2025
Gemini 3.8 Flash leads by +3.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.5 Flash
95.5
Gemini 3.8 Flash
98.9
Proofbench
Gemini 3.8 Flash leads by +17.0
Gemini 3.5 Flash
31.0
Gemini 3.8 Flash
48.0
SimpleQA Verified
Gemini 3.8 Flash leads by +3.5
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Gemini 3.5 Flash
66.2
Gemini 3.8 Flash
69.7
Surface Evolver Bench
Gemini 3.8 Flash leads by +18.7
Gemini 3.5 Flash
58.1
Gemini 3.8 Flash
76.9
Full benchmark table
| Benchmark | Gemini 3.5 Flash | Gemini 3.8 Flash |
|---|---|---|
Artificial Analysis · Quality Index | 50.2 | 40.9 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 27.5 | 64.3 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 47.4 | 59.0 |
Deepswe | 37.4 | 73.8 |
Dtbench | 91.1 | 92.9 |
FrontierMath-Tier-4-v2-Private | 26.8 | 21.9 |
FrontierMath-Tiers-1-3-v2-Private | 62.8 | 68.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 90.4 | 93.9 |
Lmca | 55.5 | 62.2 |
Mystery Game Puzzles | 25.1 | 41.6 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 95.5 | 98.9 |
Proofbench | 31.0 | 48.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 66.2 | 69.7 |
Surface Evolver Bench | 58.1 | 76.9 |
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 | |
| $0.75 | $3.75 | 1.0M tokens (~524 books) | $15.00 |