Compare · ModelsLive · 2 picked · head to head
Gemini 3.5 Flash Lite vs GPT-4.1
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.5 Flash Lite wins on 8/9 benchmarks
Gemini 3.5 Flash Lite wins 8 of 9 shared benchmarks. Leads in reasoning · knowledge · general.
Category leads
reasoning·Gemini 3.5 Flash Liteknowledge·Gemini 3.5 Flash Litegeneral·Gemini 3.5 Flash Litemath·Gemini 3.5 Flash Litecoding·GPT-4.1
Hype vs Reality
Attention vs performance
Gemini 3.5 Flash Lite
#215 by perf·#5 by attention
GPT-4.1
#189 by perf·no signal
Best value
Gemini 3.5 Flash Lite
3.3x better value than GPT-4.1
Gemini 3.5 Flash Lite
25.9 pts/$
$1.40/M
GPT-4.1
7.9 pts/$
$5.00/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
9 benchmarks · 2 models
Gemini 3.5 Flash LiteGPT-4.1
ARC-AGI
Gemini 3.5 Flash Lite leads by +48.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Gemini 3.5 Flash Lite
53.5
GPT-4.1
5.5
ARC-AGI-2
Gemini 3.5 Flash Lite leads by +9.9
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Gemini 3.5 Flash Lite
10.3
GPT-4.1
0.4
Chess Puzzles
Gemini 3.5 Flash Lite leads by +16.8
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemini 3.5 Flash Lite
17.9
GPT-4.1
1.1
Dtbench
Gemini 3.5 Flash Lite leads by +25.3
Gemini 3.5 Flash Lite
72.5
GPT-4.1
47.1
FrontierMath-Tiers-1-3-v2-Private
Gemini 3.5 Flash Lite leads by +20.0
Gemini 3.5 Flash Lite
26.0
GPT-4.1
6.0
GPQA diamond
Gemini 3.5 Flash Lite leads by +21.9
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 Lite
77.8
GPT-4.1
55.9
Lmca
Gemini 3.5 Flash Lite leads by +14.1
Gemini 3.5 Flash Lite
44.2
GPT-4.1
30.1
OTIS Mock AIME 2024-2025
Gemini 3.5 Flash Lite leads by +32.8
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.5 Flash Lite
71.1
GPT-4.1
38.3
WeirdML
GPT-4.1 leads by +0.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 3.5 Flash Lite
39.0
GPT-4.1
39.0
Full benchmark table
| Benchmark | Gemini 3.5 Flash Lite | GPT-4.1 |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 53.5 | 5.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 10.3 | 0.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 17.9 | 1.1 |
Dtbench | 72.5 | 47.1 |
FrontierMath-Tiers-1-3-v2-Private | 26.0 | 6.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 77.8 | 55.9 |
Lmca | 44.2 | 30.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 71.1 | 38.3 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 39.0 | 39.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.30 | $2.50 | 1.0M tokens (~524 books) | $8.50 | |
| $2.00 | $8.00 | 1.0M tokens (~524 books) | $35.00 |