#2 Gemini 3 Flash Preview
medium- Cost
- $0.010
- Time
- 17.9s
- Tokens
- 3,236 tok
AI BENCHY Compare
Summary
Gemini 3 Flash Preview (medium) leads on average score with 9.6 vs 5.3. Qwen3.5-122B-A10B has the lower benchmark cost at $0.020 vs $0.667. Qwen3.5-122B-A10B is faster at 3.41s vs 18.64s, with pass rates of 98.4% vs 31.8%.
Last updated at: 2026-07-14
| Metric | Gemini 3 Flash Preview Gemini 3 Flash Preview medium | Qwen3.5-122B-A10B Qwen3.5-122B-A10B none |
|---|---|---|
| Score | 9.6 | 5.3 |
| Rank | #2 | #152 |
| Reliability | 10.0 | 10.0 |
| Consistency | 9.7 | 9.6 |
| Tests Correct | ||
| Attempt pass rate | 98.4% | 31.8% |
| Flaky tests | 1 | 1 |
| Total Runs | 63 | 63 |
| Cost per result | 3.335 | 0.393 |
| Total Cost | $0.667 | $0.020 |
| Input Price | $0.500 / 1M | $0.260 / 1M |
| Output Price | $3.000 / 1M | $2.080 / 1M |
| Total Input Tokens | 37,017 | 47,735 |
| Output Tokens | 2,006 | 3,383 |
| Reasoning Tokens | 214,153 | 0 |
| Response Time (avg) | 18.64s | 3.41s |
| Response Time (max) | 117.26s | 46.00s |
| Response Time (total) | 391.35s | 71.59s |
Generation showcase
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
| Coding | Score | Consistency | Attempt pass rate | Flaky tests | Tests Correct | Response Time (avg) | Input Tokens | Output Tokens | Reasoning Tokens |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Flash Preview | 8.6 | 7.6 | 88.9% | 1 | 84.40s | 8,122 | 462 | 161,084 | |
| Qwen3.5-122B-A10B | 3.7 | 7.0 | 22.2% | 1 | 2.77s | 7,913 | 693 | 0 |
Switch Comparison Pair