# Gemini 2.5 Flash-Lite vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.6 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 2.2× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-trinity-large-thinking
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 5 categories and Trinity Large Thinking in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Trinity Large Thinking leads 40.9 to 32.5.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| Provider | Google | Arcee AI |
| Noometry Index | 37.0 | 38.6 |
| Rank | 211 | 185 |
| Context | 1.05M | 262K |
| Input $/M | $0.10 | $0.25 |
| Output $/M | $0.40 | $0.80 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash-Lite: 38.5 (#173)
- Trinity Large Thinking: 34.1 (#244)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1373 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| WeirdML | 35.2% | — |
| ALE-Bench | 325.9 | — |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 28.0 (#96)
- Trinity Large Thinking: —

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |

## Reasoning

- Gemini 2.5 Flash-Lite: 22.2 (#205)
- Trinity Large Thinking: 16.9 (#298)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1350 |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 133.94 | — |

## Math

- Gemini 2.5 Flash-Lite: 38.0 (#144)
- Trinity Large Thinking: 37.6 (#149)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1373 | 1366 |
| Omni-MATH | 48% | — |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.5 (#210)
- Trinity Large Thinking: 40.9 (#113)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 6.9% |
| LMArena Expert | 1373 | 1360 |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 29.1 (#114)
- Trinity Large Thinking: —

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.3 (#134)
- Trinity Large Thinking: 46.2 (#160)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1369 | 1325 |
| LMArena Chinese | 1404 | 1373 |
| LMArena French | 1388 | 1374 |
| LMArena German | 1389 | 1356 |
| LMArena Japanese | 1359 | 1311 |
| LMArena Korean | 1360 | 1306 |
| LMArena Russian | 1373 | 1337 |
| LMArena Spanish | 1396 | 1357 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.0 (#168)
- Trinity Large Thinking: 70.5 (#162)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1367 | 1334 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#262)
- Trinity Large Thinking: 41.3 (#144)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1373 | 1355 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 56.8 (#135)
- Trinity Large Thinking: 53.8 (#158)

| Benchmark | Gemini 2.5 Flash-Lite | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1379 | 1340 |
| LMArena Creative Writing | 1367 | 1320 |
| LMArena Multi-Turn | 1366 | 1342 |
| WildBench | 81.8% | — |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.6 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 2.2× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash-Lite or Trinity Large Thinking?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.

### Is Gemini 2.5 Flash-Lite or Trinity Large Thinking better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.5 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash-Lite does, with 1.05M tokens against 262K.

### How many benchmarks do Gemini 2.5 Flash-Lite and Trinity Large Thinking share?

18 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Trinity Large Thinking has 24.