Gemini 2.5 Pro vs Kimi K2 (Non-Reasoning)
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 1 of 6 areas
Agents
Gemini 2.5 Pro is the stronger all-rounder.Kimi K2 (Non-Reasoning) is cheaper and better at agents.
Scores updated · 20 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 thinking40Gemini 2.5 Pro4 of 4 tests
- CodingWriting and fixing software20Gemini 2.5 Pro2 of 2 tests
- FactsGetting facts right instead of making them up21Gemini 2.5 Pro2 of 3 tests
- Long documentsFinding answers in very long texts10Gemini 2.5 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 2.5 Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own01Kimi K2 (Non-Reasoning)1 of 1 test
Agents, 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.
Kimi K2 (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 Pro pulls ahead
- Common-sense trick questionsSimpleBench+25.3points ahead
- Reasons across sets of long documentsAA-LCR+16points ahead
- Code for real scientific research problemsSciCode+11.8points ahead
Where Kimi K2 (Non-Reasoning) pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.3points ahead
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 2.5 Pro
- SciCodeGemini 2.5 Pro by 11.846.334.5+11.8
- Terminal-Bench HardGemini 2.5 Pro by 10.626.515.9+10.6
ReasoningGemini 2.5 Pro
- SimpleBenchGemini 2.5 Pro by 25.351.626.3+25.3
- Humanity's Last ExamGemini 2.5 Pro by 10.6187.4+10.6
- GPQA DiamondGemini 2.5 Pro by 783.676.6+7
- CritPtGemini 2.5 Pro by 2.62.60+2.6
FactsGemini 2.5 Pro
- AA-Omniscience · Non-hallucinationKimi K2 (Non-Reasoning) by 14.39.123.4+14.3
- AA-Omniscience · AccuracyGemini 2.5 Pro by 11.73927.4+11.7
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Pro by 10.9717.9+10.9
Following instructionsGemini 2.5 Pro
- IFBenchGemini 2.5 Pro by 7.248.741.5+7.2
Other results8 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.
- AA Agentic IndexKimi K2 (Non-Reasoning) by 44.43.547.9+44.4
- AA-OmniscienceGemini 2.5 Pro by 12-16.4-28.3+12
- Artificial Analysis Coding IndexGemini 2.5 Pro by 11.946.734.8+11.9
- vectara_factual_consistencyGemini 2.5 Pro by 10.99382.1+10.9
- τ²-Bench Telecom (AA run)Kimi K2 (Non-Reasoning) by 754.161.1+7
- vectara_avg_summary_lengthGemini 2.5 Pro by 47.2 rating points106.459.2+47.2 rating
- AA IntelligenceGemini 2.5 Pro by 2.31512.7+2.3
- vectara_answer_ratetie99.198.6tie
Questions people ask
Which is better, Gemini 2.5 Pro or Kimi K2 (Non-Reasoning)?
Gemini 2.5 Pro wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Kimi K2 (Non-Reasoning) wins agents, and costs 74% less.
Which is better for coding?
Gemini 2.5 Pro. It wins 2 of the 2 coding tests both models report; Kimi K2 (Non-Reasoning) wins none.
Which is cheaper?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Kimi K2 (Non-Reasoning) costs $0.57 and $2.30. That makes Kimi K2 (Non-Reasoning) about 74% cheaper for the same work.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.