Model comparison
Gemini 3.8 Flash vs Trinity Large Thinking
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 38.6 on the Noometry Index. Trinity Large Thinking costs 3.9× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Google
Arcee AISummary
- They share 22 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 97.4% for Gemini 3.8 Flash and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.8 Flash | Trinity Large Thinking | |
|---|---|---|
| Provider | Arcee AI | |
| Noometry Index | 61.8 | 38.6 |
| Released | 2026-09-02 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 80K |
| Input $ / M tokens | $0.75 | $0.25 |
| Output $ / M tokens | $3.75 | $0.80 |
| Results tracked | 50 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.8 Flash: 59.2 (#15), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1584 | 1238 |
| SciCode | 56.6% | 36.1% |
| LMArena Coding | 1510 | 1381 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |
| WeirdML | 84.8% | — |
| ALE-Bench | 1,270 | — |
Agentic & Tool Use Not comparable
Gemini 3.8 Flash: 41.8 (#21), Trinity Large Thinking: —
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 76.9 (#5), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 97.4% | 16.5% |
| CritPt | 18.3% | 0.9% |
| LMArena Hard Prompts | 1508 | 1350 |
| Surface Evolver Bench | 76.9% | 15.6% |
| ARC-AGI-2 | 89.2% | — |
| ARC-AGI-1 | 98.5% | — |
| Chess Puzzles | 61% | — |
| Thematic Generalization | — | 41.6% |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LMCA | 52.9% | — |
| Epoch Capabilities Index | 156.71 | — |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.3 (#28), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1528 | 1366 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 48% | — |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.8 (#2), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1524 | 1360 |
| GPQA Diamond | 95.4% | — |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
Gemini 3.8 Flash: 40.7 (#45), Trinity Large Thinking: —
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 58.0 (#5), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1491 | 1325 |
| LMArena Chinese | 1554 | 1373 |
| LMArena French | 1498 | 1374 |
| LMArena German | 1493 | 1356 |
| LMArena Japanese | 1502 | 1311 |
| LMArena Korean | 1459 | 1306 |
| LMArena Russian | 1515 | 1337 |
| LMArena Spanish | 1485 | 1357 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.0 (#13), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1490 | 1334 |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.3 (#24), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1508 | 1355 |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.2 (#15), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Gemini 3.8 Flash | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1499 | 1340 |
| LMArena Creative Writing | 1492 | 1320 |
| LMArena Multi-Turn | 1501 | 1342 |
| EQ-Bench Creative Writing | 1748 | — |
Frequently asked questions
Is Gemini 3.8 Flash better than Trinity Large Thinking?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 38.6 on the Noometry Index. Trinity Large Thinking costs 3.9× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.8 Flash or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.
Is Gemini 3.8 Flash or Trinity Large Thinking better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.8 Flash and Trinity Large Thinking share?
22 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Trinity Large Thinking has 24.