mini-SWE-agent + Gemini 3.8 Flash: benchmark scores, price and ranking
mini-SWE-agent + Gemini 3.8 Flash ranks #368 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.3), based on 1 benchmark results captured up to 2026-10-13.
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Aggregate rank
- #368 of 743 (score 48.3)
Across the 1 benchmark where at least ten models are scored, mini-SWE-agent + Gemini 3.8 Flash is in the top 10% on 0 and in the top half on 0.
mini-SWE-agent + Gemini 3.8 Flash benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Terminal-Bench 4.0 | 19.1% | #17 of 23 | Terminal-Bench 4.0 official leaderboard | 2026-10-13 |
About mini-SWE-agent + Gemini 3.8 Flash
mini-SWE-agent + Gemini 3.8 Flash is a smaller, lower-cost model. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where mini-SWE-agent + Gemini 3.8 Flash stands
On our aggregate score, mini-SWE-agent + Gemini 3.8 Flash is #368 of 743 ranked models, around the middle of the table. Its score is 48.3; the scale is centred on 50, so it sits 1.7 points below the typical model. That beats 50% of the ranked field.
mini-SWE-agent + Gemini 3.8 Flash, benchmark by benchmark
mini-SWE-agent + Gemini 3.8 Flash lands below the middle on Terminal-Bench 4.0: 19.1%, #17 of 23, with 70% of the field scoring higher. Claude Code + Opus 5.5 leads at 64.8%; the closest result above is Grok Build + Grok 4.6 at 20.3%. It covers real terminal tasks, agent+model config. The board median is 35.8%, so mini-SWE-agent + Gemini 3.8 Flash is 16.7 points below it. Source: Terminal-Bench 4.0 official leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: Terminal-Bench 4.0 official leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #365 gemini-2.0-flash-02-05 (48.3)
- #366 Ring-2.6-1T (48.3)
- #367 Qwen2.5 Coder 32B Instruct (48.3)
- #369 DevStral Small 2507 (48.3)
- #370 ernie-5.1 (48.3)
- #371 Opus 4.5 (Thinking, 8K) (48.2)
Compare it on the live leaderboard → · How the aggregate score works