Compare · ModelsLive · 2 picked · head to head
Gemini 3.1 Flash Lite vs gpt-oss-120b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.1 Flash Lite wins on 6/7 benchmarks
Gemini 3.1 Flash Lite wins 6 of 7 shared benchmarks. Leads in speed · knowledge · general.
Category leads
speed·Gemini 3.1 Flash Liteknowledge·Gemini 3.1 Flash Litegeneral·Gemini 3.1 Flash Litemath·gpt-oss-120bcoding·Gemini 3.1 Flash Lite
Hype vs Reality
Attention vs performance
Gemini 3.1 Flash Lite
#162 by perf·#5 by attention
gpt-oss-120b
#127 by perf·no signal
Best value
gpt-oss-120b
9.3x better value than Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite
50.9 pts/$
$0.88/M
gpt-oss-120b
475.4 pts/$
$0.10/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
7 benchmarks · 2 models
Gemini 3.1 Flash Litegpt-oss-120b
Artificial Analysis · Quality Index
Gemini 3.1 Flash Lite leads by +13.4
Gemini 3.1 Flash Lite
25.0
gpt-oss-120b
11.6
Chess Puzzles
Gemini 3.1 Flash Lite leads by +5.3
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemini 3.1 Flash Lite
21.1
gpt-oss-120b
15.8
Dtbench
Gemini 3.1 Flash Lite leads by +0.9
Gemini 3.1 Flash Lite
61.3
gpt-oss-120b
60.5
GPQA diamond
Gemini 3.1 Flash Lite leads by +8.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 3.1 Flash Lite
75.8
gpt-oss-120b
67.7
Lmca
Gemini 3.1 Flash Lite leads by +15.1
Gemini 3.1 Flash Lite
41.2
gpt-oss-120b
26.1
OTIS Mock AIME 2024-2025
gpt-oss-120b leads by +8.9
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.1 Flash Lite
80.0
gpt-oss-120b
88.9
WeirdML
Gemini 3.1 Flash Lite leads by +4.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 3.1 Flash Lite
52.2
gpt-oss-120b
48.2
Full benchmark table
| Benchmark | Gemini 3.1 Flash Lite | gpt-oss-120b |
|---|---|---|
Artificial Analysis · Quality Index | 25.0 | 11.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 21.1 | 15.8 |
Dtbench | 61.3 | 60.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 75.8 | 67.7 |
Lmca | 41.2 | 26.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 80.0 | 88.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 52.2 | 48.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.25 | $1.50 | 1.0M tokens (~524 books) | $5.63 | |
| $0.04 | $0.17 | 131K tokens (~66 books) | $0.70 |