Compare · ModelsLive · 2 picked · head to head
Gemini 3.8 Flash vs Gemini 3.1 Pro Preview
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.8 Flash wins on 15/22 benchmarks
Gemini 3.8 Flash wins 15 of 22 shared benchmarks. Leads in speed · agentic · knowledge.
Category leads
speed·Gemini 3.8 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 3.8 Flash
#63 by perf·#8 by attention
Gemini 3.1 Pro Preview
#137 by perf·#8 by attention
Best value
Gemini 3.8 Flash
3.7x better value than Gemini 3.1 Pro Preview
Gemini 3.8 Flash
25.5 pts/$
$2.25/M
Gemini 3.1 Pro Preview
6.9 pts/$
$7.00/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
Google DeepMind
$4.20T·Tier 1
Head to head
22 benchmarks · 2 models
Gemini 3.8 FlashGemini 3.1 Pro Preview
Artificial Analysis · CritPt
Gemini 3.8 Flash leads by +0.6
Gemini 3.8 Flash
18.3
Gemini 3.1 Pro Preview
17.7
Artificial Analysis · GDPval
Gemini 3.8 Flash leads by +31.8
Gemini 3.8 Flash
45.6
Gemini 3.1 Pro Preview
13.8
Artificial Analysis · GPQA Diamond
Gemini 3.8 Flash leads by +1.2
Gemini 3.8 Flash
95.3
Gemini 3.1 Pro Preview
94.1
Artificial Analysis · Humanity's Last Exam
Gemini 3.8 Flash leads by +0.8
Gemini 3.8 Flash
47.8
Gemini 3.1 Pro Preview
47.0
Artificial Analysis · Long Context Reasoning
Gemini 3.1 Pro Preview leads by +0.7
Gemini 3.8 Flash
81.3
Gemini 3.1 Pro Preview
82.0
Artificial Analysis · MMMU Pro
Gemini 3.8 Flash leads by +3.2
Gemini 3.8 Flash
85.6
Gemini 3.1 Pro Preview
82.4
Artificial Analysis · Quality Index
Gemini 3.8 Flash leads by +11.2
Gemini 3.8 Flash
40.9
Gemini 3.1 Pro Preview
29.7
Artificial Analysis · SciCode
Gemini 3.1 Pro Preview leads by +2.1
Gemini 3.8 Flash
56.6
Gemini 3.1 Pro Preview
58.7
APEX-Agents
Gemini 3.8 Flash leads by +29.0
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
Gemini 3.1 Pro Preview
35.3
Chess Puzzles
Gemini 3.8 Flash leads by +6.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemini 3.8 Flash
59.0
Gemini 3.1 Pro Preview
52.6
Deepswe
Gemini 3.8 Flash leads by +62.1
Gemini 3.8 Flash
73.8
Gemini 3.1 Pro Preview
11.7
Dtbench
Gemini 3.1 Pro Preview leads by +2.3
Gemini 3.8 Flash
92.9
Gemini 3.1 Pro Preview
95.1
FrontierMath-Tier-4-v2-Private
Gemini 3.1 Pro Preview leads by +4.9
Gemini 3.8 Flash
21.9
Gemini 3.1 Pro Preview
26.8
FrontierMath-Tiers-1-3-v2-Private
Gemini 3.8 Flash leads by +8.8
Gemini 3.8 Flash
68.4
Gemini 3.1 Pro Preview
59.6
Furniture Assembly
Gemini 3.8 Flash leads by +2.4
Gemini 3.8 Flash
2.4
Gemini 3.1 Pro Preview
0.0
GPQA diamond
Gemini 3.8 Flash leads by +1.3
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
Gemini 3.1 Pro Preview
92.6
HLE
Gemini 3.1 Pro Preview leads by +2.0
HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. Claude Opus 4.7 scores 46.9% without tools and 54.7% with tools · making it one of the few benchmarks where the top score is below 60%.
Gemini 3.8 Flash
41.7
Gemini 3.1 Pro Preview
43.7
Lmca
Gemini 3.1 Pro Preview leads by +1.1
Gemini 3.8 Flash
62.2
Gemini 3.1 Pro Preview
63.3
Mystery Game Puzzles
Gemini 3.8 Flash leads by +14.3
Gemini 3.8 Flash
41.6
Gemini 3.1 Pro Preview
27.3
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 3.8 Flash
98.9
Gemini 3.1 Pro Preview
95.6
Proofbench
Gemini 3.8 Flash leads by +22.0
Gemini 3.8 Flash
48.0
Gemini 3.1 Pro Preview
26.0
SimpleQA Verified
Gemini 3.1 Pro Preview leads by +3.8
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Gemini 3.8 Flash
69.7
Gemini 3.1 Pro Preview
73.5
Full benchmark table
| Benchmark | Gemini 3.8 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
Artificial Analysis · CritPt | 18.3 | 17.7 |
Artificial Analysis · GDPval | 45.6 | 13.8 |
Artificial Analysis · GPQA Diamond | 95.3 | 94.1 |
Artificial Analysis · Humanity's Last Exam | 47.8 | 47.0 |
Artificial Analysis · Long Context Reasoning | 81.3 | 82.0 |
Artificial Analysis · MMMU Pro | 85.6 | 82.4 |
Artificial Analysis · Quality Index | 40.9 | 29.7 |
Artificial Analysis · SciCode | 56.6 | 58.7 |
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 | 35.3 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 59.0 | 52.6 |
Deepswe | 73.8 | 11.7 |
Dtbench | 92.9 | 95.1 |
FrontierMath-Tier-4-v2-Private | 21.9 | 26.8 |
FrontierMath-Tiers-1-3-v2-Private | 68.4 | 59.6 |
Furniture Assembly | 2.4 | 0.0 |
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 | 92.6 |
HLE HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. Claude Opus 4.7 scores 46.9% without tools and 54.7% with tools · making it one of the few benchmarks where the top score is below 60%. | 41.7 | 43.7 |
Lmca | 62.2 | 63.3 |
Mystery Game Puzzles | 41.6 | 27.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.9 | 95.6 |
Proofbench | 48.0 | 26.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 69.7 | 73.5 |
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 | |
| $2.00 | $12.00 | 1.0M tokens (~524 books) | $45.00 |