Compare · ModelsLive · 2 picked · head to head
GPT-5 Nano vs Gemini 1.5 Pro (Feb 2024)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5 Nano wins on 9/10 benchmarks
GPT-5 Nano wins 9 of 10 shared benchmarks. Leads in reasoning · knowledge · language.
Category leads
reasoning·GPT-5 Nanoknowledge·GPT-5 Nanolanguage·GPT-5 Nanomath·GPT-5 Nanocoding·GPT-5 Nano
Hype vs Reality
Attention vs performance
GPT-5 Nano
#114 by perf·no signal
Gemini 1.5 Pro (Feb 2024)
#138 by perf·no signal
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Google DeepMind
$4.00T·Tier 1
Head to head
10 benchmarks · 2 models
GPT-5 NanoGemini 1.5 Pro (Feb 2024)
ARC-AGI-2
GPT-5 Nano leads by +1.8
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-5 Nano
2.6
Gemini 1.5 Pro (Feb 2024)
0.8
GPQA diamond
GPT-5 Nano leads by +31.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5 Nano
59.3
Gemini 1.5 Pro (Feb 2024)
27.8
HELM · GPQA
GPT-5 Nano leads by +14.5
GPT-5 Nano
67.9
Gemini 1.5 Pro (Feb 2024)
53.4
HELM · IFEval
GPT-5 Nano leads by +9.5
GPT-5 Nano
93.2
Gemini 1.5 Pro (Feb 2024)
83.7
HELM · MMLU-Pro
GPT-5 Nano leads by +4.1
GPT-5 Nano
77.8
Gemini 1.5 Pro (Feb 2024)
73.7
HELM · Omni-MATH
GPT-5 Nano leads by +18.3
GPT-5 Nano
54.7
Gemini 1.5 Pro (Feb 2024)
36.4
HELM · WildBench
Gemini 1.5 Pro (Feb 2024) leads by +0.7
GPT-5 Nano
80.6
Gemini 1.5 Pro (Feb 2024)
81.3
MATH level 5
GPT-5 Nano leads by +54.5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-5 Nano
95.2
Gemini 1.5 Pro (Feb 2024)
40.8
OTIS Mock AIME 2024-2025
GPT-5 Nano leads by +74.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5 Nano
81.1
Gemini 1.5 Pro (Feb 2024)
6.7
WeirdML
GPT-5 Nano leads by +15.9
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5 Nano
38.1
Gemini 1.5 Pro (Feb 2024)
22.2
Full benchmark table
| Benchmark | GPT-5 Nano | Gemini 1.5 Pro (Feb 2024) |
|---|---|---|
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. | 2.6 | 0.8 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 59.3 | 27.8 |
HELM · GPQA | 67.9 | 53.4 |
HELM · IFEval | 93.2 | 83.7 |
HELM · MMLU-Pro | 77.8 | 73.7 |
HELM · Omni-MATH | 54.7 | 36.4 |
HELM · WildBench | 80.6 | 81.3 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 95.2 | 40.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 81.1 | 6.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 38.1 | 22.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.05 | $0.40 | 400K tokens (~200 books) | $1.38 | |
| — | — | — | — |
People also compared