Compare · ModelsLive · 2 picked · head to head
Gemini 2.5 Pro vs R1
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 2.5 Pro wins on 14/14 benchmarks
Gemini 2.5 Pro wins 14 of 14 shared benchmarks. Leads in coding · reasoning · arena.
Category leads
coding·Gemini 2.5 Proreasoning·Gemini 2.5 Proarena·Gemini 2.5 Proknowledge·Gemini 2.5 Promath·Gemini 2.5 Pro
Hype vs Reality
Attention vs performance
Gemini 2.5 Pro
#61 by perf·no signal
R1
#116 by perf·no signal
Best value
R1
2.8x better value than Gemini 2.5 Pro
Gemini 2.5 Pro
10.0 pts/$
$5.63/M
R1
28.2 pts/$
$1.60/M
Vendor risk
Mixed exposure
One or more vendors flagged
Google DeepMind
$4.00T·Tier 1
DeepSeek
$3.4B·Tier 1
Head to head
14 benchmarks · 2 models
Gemini 2.5 ProR1
Aider polyglot
Gemini 2.5 Pro leads by +26.2
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
Gemini 2.5 Pro
83.1
R1
56.9
ARC-AGI
Gemini 2.5 Pro leads by +25.2
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Gemini 2.5 Pro
41.0
R1
15.8
ARC-AGI-2
Gemini 2.5 Pro leads by +3.6
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Gemini 2.5 Pro
4.9
R1
1.3
Chatbot Arena Elo · Overall
Gemini 2.5 Pro leads by +50.7
Gemini 2.5 Pro
1448.2
R1
1397.5
Balrog
Gemini 2.5 Pro leads by +8.4
Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning.
Gemini 2.5 Pro
43.3
R1
34.9
DeepResearch Bench
Gemini 2.5 Pro leads by +14.6
DeepResearch Bench · evaluates AI on complex multi-step research tasks requiring information gathering, synthesis, and producing comprehensive analyses.
Gemini 2.5 Pro
49.7
R1
35.1
Fiction.LiveBench
Gemini 2.5 Pro leads by +22.3
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
Gemini 2.5 Pro
91.7
R1
69.4
GPQA diamond
Gemini 2.5 Pro leads by +18.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 2.5 Pro
80.4
R1
62.3
Lech Mazur Writing
Gemini 2.5 Pro leads by +3.0
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
Gemini 2.5 Pro
86.0
R1
83.0
MATH level 5
Gemini 2.5 Pro leads by +2.5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Gemini 2.5 Pro
95.6
R1
93.0
OTIS Mock AIME 2024-2025
Gemini 2.5 Pro leads by +31.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 2.5 Pro
84.7
R1
53.3
SimpleBench
Gemini 2.5 Pro leads by +37.8
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Gemini 2.5 Pro
54.9
R1
17.1
SimpleQA Verified
Gemini 2.5 Pro leads by +28.6
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Gemini 2.5 Pro
56.0
R1
27.4
WeirdML
Gemini 2.5 Pro leads by +17.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 2.5 Pro
54.0
R1
36.5
Full benchmark table
| Benchmark | Gemini 2.5 Pro | R1 |
|---|---|---|
Aider polyglot Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework. | 83.1 | 56.9 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 41.0 | 15.8 |
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. | 4.9 | 1.3 |
Chatbot Arena Elo · Overall | 1448.2 | 1397.5 |
Balrog Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning. | 43.3 | 34.9 |
DeepResearch Bench DeepResearch Bench · evaluates AI on complex multi-step research tasks requiring information gathering, synthesis, and producing comprehensive analyses. | 49.7 | 35.1 |
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 91.7 | 69.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 80.4 | 62.3 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 86.0 | 83.0 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 95.6 | 93.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 84.7 | 53.3 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 54.9 | 17.1 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 56.0 | 27.4 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 54.0 | 36.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.25 | $10.00 | 1.0M tokens (~524 books) | $34.38 | |
| $0.70 | $2.50 | 64K tokens (~32 books) | $11.50 |