Advertise here
#155

Gemini 2.5 Flash

Google Release: 2025-06-17 Tested on: 2026-10-01 02:17 google/gemini-2.5-flash::medium
~350B total (~20B active)MoEClosedEstimated
(medium) (none)

Summary

Gemini 2.5 Flash scores 7.3 on AI BENCHY and ranks #155. It has 10.0 reliability, a 68.1% pass rate, $0.680 total cost, and 20.51s average response time.

What makes Gemini 2.5 Flash unique: It stands out most in Domain specific, where it ranks #2, while Agentic is its weakest area at #15.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~350B total (~20B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Google does not disclose parameter counts.

Parameter source Availability source

Score

7.3

Consistency

9.6

Reliability

10.0

Total Cost (Current Price)

$0.680 ↑ +5.6%

Tested at: $0.644

Total Output Tokens

241,365

Total Input Tokens

132,507

Input Price

$0.300 / 1M

Output Price

$2.500 / 1M

Cache Read Price

$0.030 / 1M

Cache Write Price

$0.084 / 1M

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 8

Attempt pass rate: 68.1%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

20.51s

Response Time (max): 140.50s

Response Time (total): 471.64s

Wrong answer: 6 Did not follow instructions: 2

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#155 Gemini 2.5 Flash

medium
No output was saved. The original provider response or failure reason is unavailable.
Cost
$0.000
Time
274.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 02:17 Re-test 7.3 10.0 $0.680 ↑ Current run
2026-07-16 23:00 New test added 8.2 10.0 $0.643 Compare
2026-06-04 14:01 New test added 7.8 10.0 $0.379 Compare
2026-05-22 00:32 Suite changed 7.7 10.0 $0.358 Compare
2026-04-11 01:44 First recorded run 8.2 N/A $0.319 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 02:17 · Current run69/69 attempts7.39.610.015/231241,365132,507$0.68020.51s
2026-05-22 00:32 · Suite changed60/60 attempts7.79.610.013/201139,1790$0.35815.69s
Difference—-0.40.00.0+20+102186+132507+$0.322+4818ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 60/60 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-08-14 12:51 $0.300 / 1M $2.500 / 1M N/A N/A
2026-10-01 18:33 $0.300 / 1M $2.500 / 1M $0.030 / 1M $0.084 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Gemini 2.5 FlashmediumvsGrok 4.7mediumGemini 2.5 FlashmediumvsLongCat 2.0highGemini 2.5 FlashmediumvsClaude Fable 5.1mediumGemini 2.5 FlashmediumvsQwen3.6 PlusmediumGemini 2.5 FlashmediumvsGLM 5.3 FlashhighGemini 2.5 FlashmediumvsGemini 3.5 Flash LitemediumGemini 2.5 FlashmediumvsGemma 4 26B A4BmediumFree AvailableGemini 2.5 FlashmediumvsQwen3.5-27BnoneGemini 2.5 FlashmediumvsInklingmediumFree AvailableGemini 2.5 FlashmediumvsQwen3.5 Plus 2026-02-15medium

Category Breakdown

Category Score Consistency Tests Correct
Agentic 3.0 10.0
Anti-AI Tricks 8.4 10.0
Coding 7.8 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.9 7.2
General Intelligence 4.8 10.0
Instructions following 9.8 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models