Gemini 2.5 Flash vs Kimi K2 (Non-Reasoning)
Wins 4 of 6 areas
Reasoning · Facts · Long documents · Following instructions
Wins 2 of 6 areas
Coding · Agents
Gemini 2.5 Flash is the stronger all-rounder.Kimi K2 (Non-Reasoning) is better at coding.
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 Flash4 of 4 tests
- FactsGetting facts right instead of making them up21Gemini 2.5 Flash2 of 3 tests
- Long documentsFinding answers in very long texts10Gemini 2.5 Flash1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 2.5 Flash1 of 1 test
- CodingWriting and fixing software02Kimi K2 (Non-Reasoning)2 of 2 tests
- 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.
Gemini 2.5 Flash costs 2% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 2.5 Flash pulls ahead
- Common-sense trick questionsSimpleBench+14.9points ahead
- Reasons across sets of long documentsAA-LCR+12.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+8.8points ahead
Where Kimi K2 (Non-Reasoning) pulls ahead
- Real work tasks from 44 professionsGDPVal+14.7points ahead
- Code for real scientific research problemsSciCode+5.4points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+2.3points 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.
CodingKimi K2 (Non-Reasoning)
- SciCodeKimi K2 (Non-Reasoning) by 5.429.134.5+5.4
- Terminal-Bench HardKimi K2 (Non-Reasoning) by 2.313.615.9+2.3
ReasoningGemini 2.5 Flash
- SimpleBenchGemini 2.5 Flash by 14.941.226.3+14.9
- Humanity's Last ExamGemini 2.5 Flash by 4.712.17.4+4.7
- GPQA DiamondGemini 2.5 Flash by 2.47976.6+2.4
- CritPtGemini 2.5 Flash by 1.11.10+1.1
FactsGemini 2.5 Flash
- Vectara HHEM hallucination ratelower is betterGemini 2.5 Flash by 10.17.817.9+10.1
- AA-Omniscience · AccuracyKimi K2 (Non-Reasoning) by 1.425.927.4+1.4
- AA-Omniscience · Non-hallucinationGemini 2.5 Flash by 1.324.723.4+1.3
Following instructionsGemini 2.5 Flash
- IFBenchGemini 2.5 Flash by 8.850.341.5+8.8
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.
- τ²-Bench Telecom (AA run)Kimi K2 (Non-Reasoning) by 29.531.661.1+29.5
- AA Agentic IndexKimi K2 (Non-Reasoning) by 29.118.847.9+29.1
- Artificial Analysis Coding IndexKimi K2 (Non-Reasoning) by 12.622.234.8+12.6
- vectara_factual_consistencyGemini 2.5 Flash by 10.192.282.1+10.1
- vectara_avg_summary_lengthGemini 2.5 Flash by 42.3 rating points101.559.2+42.3 rating
- AA-OmniscienceKimi K2 (Non-Reasoning) by 1.5-29.8-28.3+1.5
- AA Intelligencetie13.112.7tie
- vectara_answer_ratetie9998.6tie
Questions people ask
Which is better, Gemini 2.5 Flash or Kimi K2 (Non-Reasoning)?
Gemini 2.5 Flash wins four of the six areas where both have results: reasoning, facts, long documents and following instructions. Kimi K2 (Non-Reasoning) wins coding and agents.
Which is better for coding?
Kimi K2 (Non-Reasoning). It wins 2 of the 2 coding tests both models report; Gemini 2.5 Flash wins none.
Which is cheaper?
Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens; Kimi K2 (Non-Reasoning) costs $0.57 and $2.30. That makes Gemini 2.5 Flash about 2% 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.