Models / gemini-3-flash

Google

gemini-3-flash

30 published results from 3 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider
Google
Sources
3
Our benchmarks
0
Price
Not yet published

Reported by others

Reported by Arena (formerly LMArena)
1,439
Overall · rank 28 of 44
Unit
Arena rating, higher is better
Range
1,430 to 1,449
Sample
7158 votes
Configuration
gemini-3-flash
Measured
13 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,191
Overall · rank 8 of 34
Unit
Arena rating, higher is better
Range
1,187 to 1,196
Sample
149334 votes
Configuration
gemini-3-flash
Measured
24 Aug 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,468
Overall · rank 22 of 177
Unit
Arena rating, higher is better
Range
1,464 to 1,472
Sample
30632 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Reported by Arena (formerly LMArena)
1,451
Overall · rank 47 of 177
Unit
Arena rating, higher is better
Range
1,449 to 1,454
Sample
89978 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Reported by Arena (formerly LMArena)
1,469
Business, management and finance · rank 18 of 402
Unit
Arena rating, higher is better
Range
1,461 to 1,477
Sample
5763 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,455
Business, management and finance · rank 40 of 402
Unit
Arena rating, higher is better
Range
1,449 to 1,460
Sample
18138 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,457
Creative writing · rank 12 of 407
Unit
Arena rating, higher is better
Range
1,447 to 1,466
Sample
4825 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,447
Creative writing · rank 24 of 407
Unit
Arena rating, higher is better
Range
1,441 to 1,453
Sample
14997 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,496
Expert prompts · rank 14 of 359
Unit
Arena rating, higher is better
Range
1,484 to 1,509
Sample
2177 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,463
Expert prompts · rank 66 of 359
Unit
Arena rating, higher is better
Range
1,456 to 1,470
Sample
8554 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,458
Instruction following · rank 31 of 409
Unit
Arena rating, higher is better
Range
1,451 to 1,465
Sample
8494 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,443
Instruction following · rank 55 of 409
Unit
Arena rating, higher is better
Range
1,438 to 1,448
Sample
29816 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,473
Overall · rank 22 of 409
Unit
Arena rating, higher is better
Range
1,468 to 1,477
Sample
31283 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,458
Overall · rank 49 of 409
Unit
Arena rating, higher is better
Range
1,455 to 1,461
Sample
90749 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,461
Writing, literature and language · rank 15 of 408
Unit
Arena rating, higher is better
Range
1,453 to 1,469
Sample
7058 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,448
Writing, literature and language · rank 30 of 408
Unit
Arena rating, higher is better
Range
1,443 to 1,453
Sample
21848 votes
Configuration
gemini-3-flash
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by OpenHands Index
49.0%
Average · rank 20 of 34
Unit
% resolved, higher is better
Configuration
gemini-3-flash
Measured
30 Jun 2026
Not shown
Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
Reported by OpenHands Index
22.1%
Front end (SWE-Bench Multimodal) · rank 30 of 34
Unit
% resolved, higher is better
Configuration
gemini-3-flash
Measured
30 Jun 2026
Not shown
Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
Reported by OpenHands Index
18.8%
Greenfield (Commit0) · rank 21 of 34
Unit
% resolved, higher is better
Configuration
gemini-3-flash
Measured
30 Jun 2026
Not shown
Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
Reported by OpenHands Index
58.8%
Information gathering (GAIA) · rank 19 of 34
Unit
% resolved, higher is better
Configuration
gemini-3-flash
Measured
30 Jun 2026
Not shown
Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
Reported by OpenHands Index
74.6%
Issue resolution (SWE-Bench) · rank 13 of 34
Unit
% resolved, higher is better
Configuration
gemini-3-flash
Measured
30 Jun 2026
Not shown
Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
Reported by OpenHands Index
70.7%
Testing (SWT-Bench) · rank 11 of 34
Unit
% resolved, higher is better
Configuration
gemini-3-flash
Measured
30 Jun 2026
Not shown
Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.
Reported by tau2-bench
68.0%
Consistency (pass^4) · rank 4 of 8
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
Reported by tau2-bench
82.5%
Task success (pass^1) · rank 3 of 8
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
Reported by tau2-bench
7.2%
Consistency (pass^4) · rank 2 of 3
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
Reported by tau2-bench
27.3%
Task success (pass^1) · rank 1 of 3
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
Reported by tau2-bench
51.8%
Consistency (pass^4) · rank 2 of 8
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
Reported by tau2-bench
76.8%
Task success (pass^1) · rank 4 of 8
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
Reported by tau2-bench
70.2%
Consistency (pass^4) · rank 5 of 8
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.
Reported by tau2-bench
91.2%
Task success (pass^1) · rank 3 of 8
Unit
% of tasks, higher is better
Configuration
gemini-3-flash
Measured
2 Mar 2026
Not shown
Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.

Compare gemini-3-flash with