Gemini 2.5 Flash Lite vs Mistral Small 3 (Non-Reasoning)
Wins 4 of 5 areas
Reasoning · Facts · Long documents · Following instructions
Wins 1 of 5 areas
Coding
Gemini 2.5 Flash Lite is the stronger all-rounder.Mistral Small 3 (Non-Reasoning) is cheaper and better at coding.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the five areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking20Gemini 2.5 Flash Lite2 of 2 tests
- FactsGetting facts right instead of making them up10Gemini 2.5 Flash Lite1 of 1 test
- Long documentsFinding answers in very long texts10Gemini 2.5 Flash Lite1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 2.5 Flash Lite1 of 1 test
- CodingWriting and fixing software01Mistral Small 3 (Non-Reasoning)1 of 1 test
Coding, facts, long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Mistral Small 3 (Non-Reasoning) costs 74% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemini 2.5 Flash Lite pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+23.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+3points ahead
Where Mistral Small 3 (Non-Reasoning) pulls ahead
- Code for real scientific research problemsSciCode+4.3points ahead
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMistral Small 3 (Non-Reasoning)
- SciCodeMistral Small 3 (Non-Reasoning) by 4.319.323.6+4.3
ReasoningGemini 2.5 Flash Lite
- GPQA DiamondGemini 2.5 Flash Lite by 16.362.546.2+16.3
- Humanity's Last ExamGemini 2.5 Flash Lite by 36.83.8+3
FactsGemini 2.5 Flash Lite
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Flash Lite by 1.83.35.1+1.8
Long documentsGemini 2.5 Flash Lite
- AA-LCRGemini 2.5 Flash Lite by 55.755.70+55.7
Following instructionsGemini 2.5 Flash Lite
- IFBenchGemini 2.5 Flash Lite by 23.549.926.4+23.5
Other results11 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AIR-Bench 2024Gemini 2.5 Flash Lite by 3365.832.8+33
- HarmBenchGemini 2.5 Flash Lite by 21.86745.2+21.8
- simple_safety_testsGemini 2.5 Flash Lite by 3.296.593.3+3.2
- vectara_avg_summary_lengthMistral Small 3 (Non-Reasoning) by 3.195.798.8+3.1
- XSTestGemini 2.5 Flash Lite by 2.597.895.3+2.5
- anthropic_red_teamGemini 2.5 Flash Lite by 2.398.796.4+2.3
- AA IntelligenceGemini 2.5 Flash Lite by 1.88.56.7+1.8
- vectara_factual_consistencyGemini 2.5 Flash Lite by 1.896.794.9+1.8
- bbqGemini 2.5 Flash Lite by 1.694.993.3+1.6
- vectara_answer_rateGemini 2.5 Flash Lite by 1.699.597.9+1.6
- τ²-Bench Telecom (AA run)Mistral Small 3 (Non-Reasoning) by 1.218.419.6+1.2
Questions people ask
Which is better, Gemini 2.5 Flash Lite or Mistral Small 3 (Non-Reasoning)?
Gemini 2.5 Flash Lite wins four of the five areas where both have results: reasoning, facts, long documents and following instructions. Mistral Small 3 (Non-Reasoning) wins coding, and costs 74% less.
Which is better for coding?
Mistral Small 3 (Non-Reasoning). It wins the one coding test both models report.
Which is cheaper?
Gemini 2.5 Flash Lite costs $0.10 per million input tokens and $0.40 per million output tokens; Mistral Small 3 (Non-Reasoning) costs $0.05 and $0.08. That makes Mistral Small 3 (Non-Reasoning) about 74% cheaper for the same work.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.