Trinity Large Thinking vs Gemma 4 31B
Updated October 21, 2026. 40 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 5.4 for Trinity Large Thinking.
Pick Trinity Large Thinking when what matters is τ²-Bench Telecom or CaseLaw (Vals AI), where it leads.
- Shared results
- 40
- Trinity Large Thinking only
- 12
- Gemma 4 31B only
- 28
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Gemma 4 31B
Gemma 4 31B scores 38.3 against 5.4.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemma 4 31B
Gemma 4 31B leads, 14.7 against 10.8.
Same board, both measured
Agentic work
AA Agentic Index
Gemma 4 31B
Gemma 4 31B leads, 4.2 against 1.0.
Same board, both measured
Web design
Design Arena: websites
No call
Only Trinity Large Thinking has a Design Arena: websites result, 1137.
Directional only
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
Trinity Large Thinking $0.0006, Gemma 4 31B $0.0004 per turn.
List prices
At a glance
- Coding index
- Trinity Large Thinking 5.4 from 1 benchmark, Gemma 4 31B 38.3 from 2 benchmarks.
- Widest category
- General, 18.9 points apart on average over 17 shared benchmarks.
- Widest single gap
- Long context reasoning (AA-LCR): Trinity Large Thinking 38.0% against Gemma 4 31B 69.7%, 31.7 points apart on a 0 to 100 scale.
- Output price
- Trinity Large Thinking $0.80 against Gemma 4 31B $0.40 per million output tokens, 2.0x apart.
- Context window
- Both take 262K tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Trinity Large Thinking | Bars | Gemma 4 31B | Ties |
|---|---|---|---|---|
| Coding | 0 | 8 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 4 | ||
| General | 0 | 17 | ||
| All shared boards | 2 | 38 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index08
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 49.0% | Only Gemma 4 31B measured |
| LMArena WebDev | 1238 | 1367 | Gemma 4 31B |
| AA Coding Index | 25.8 | 43.4 | Gemma 4 31B |
| SciCode | 40.6% | 45.5% | Gemma 4 31B |
| Terminal-Bench Hard (Artificial Analysis run) | 22.7% | 36.4% | Gemma 4 31B |
| WeirdML | Not measured | 52.3% | Only Gemma 4 31B measured |
| ALE-Bench | Not measured | 925.5 | Only Gemma 4 31B measured |
| LMArena Text: coding | 1357 | 1459 | Gemma 4 31B |
| LMArena Text: software and IT | 1362 | 1463 | Gemma 4 31B |
| LMArena WebDev: React | 1231 | 1359 | Gemma 4 31B |
| LMArena WebDev: HTML | 1240 | 1380 | Gemma 4 31B |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 14.7 | Gemma 4 31B |
| Epoch Capabilities Index | Not measured | 143.0 | Only Gemma 4 31B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Agentic Index | 1.0 | 4.2 | Gemma 4 31B |
| LiveBench research | Not measured | 44.4% | Only Gemma 4 31B measured |
| LiveBench browser | Not measured | 4.0% | Only Gemma 4 31B measured |
| LiveBench long agentic | Not measured | 13.3% | Only Gemma 4 31B measured |
| τ²-Bench Telecom | 90.1% | 65.5% | Trinity Large Thinking |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 68.3% | Only Gemma 4 31B measured |
| GPQA Diamond (Artificial Analysis run) | 75.2% | 85.7% | Gemma 4 31B |
| Humanity's Last Exam (Artificial Analysis run) | 15.8% | 23.6% | Gemma 4 31B |
| GPQA Diamond (Epoch AI run) | Not measured | 75.8% | Only Gemma 4 31B measured |
| LMArena Text: hard prompts | 1342 | 1448 | Gemma 4 31B |
| LMArena Text: expert | 1359 | 1464 | Gemma 4 31B |
| LMArena Text: hard prompts in English | 1356 | 1456 | Gemma 4 31B |
| LMArena Vision: diagrams | Not measured | 1283 | Only Gemma 4 31B measured |
| LMArena Vision: homework | Not measured | 1310 | Only Gemma 4 31B measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 73.3% | Only Gemma 4 31B measured |
| LMArena Text: math | 1365 | 1463 | Gemma 4 31B |
| LMArena Text: mathematical work | 1350 | 1465 | Gemma 4 31B |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 57.9% | 52.6% | Trinity Large Thinking |
| CorpFin (Vals AI) | 54.7% | Not measured | Only Trinity Large Thinking measured |
| MortgageTax (Vals AI) | Not measured | 61.4% | Only Gemma 4 31B measured |
| SimpleQA Verified | Not measured | 10.4% | Only Gemma 4 31B measured |
| LMArena Text: science | 1355 | 1457 | Gemma 4 31B |
| LMArena Text: medicine and healthcare | 1349 | 1451 | Gemma 4 31B |
| LMArena Text: legal and government | 1345 | 1438 | Gemma 4 31B |
| LMArena Text: business and finance | 1329 | 1430 | Gemma 4 31B |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| Design Arena: websites | 1137 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: UI components | 1045 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: game dev | 1079 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: data viz | 1098 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: 3D | 1082 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: all code categories | 1117 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: SVG | 1016 | Not measured | Only Trinity Large Thinking measured |
| Design Arena: ASCII art | 1041 | Not measured | Only Trinity Large Thinking measured |
| LiveBench design | Not measured | 58.4% | Only Gemma 4 31B measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 53.3% | Only Gemma 4 31B measured |
| SAGE (Vals AI) | Not measured | 55.0% | Only Gemma 4 31B measured |
| IFBench | 56.3% | 75.6% | Gemma 4 31B |
| Long context reasoning (AA-LCR) | 38.0% | 69.7% | Gemma 4 31B |
| DTBench | Not measured | 82.7% | Only Gemma 4 31B measured |
| LMCA | Not measured | 39.3% | Only Gemma 4 31B measured |
| Surface Evolver Bench | 15.6% | 30.6% | Gemma 4 31B |
| LMArena Text | 1340 | 1443 | Gemma 4 31B |
| LMArena Text: instruction following | 1326 | 1433 | Gemma 4 31B |
| LMArena Text: creative writing | 1308 | 1417 | Gemma 4 31B |
| LMArena Vision | Not measured | 1276 | Only Gemma 4 31B measured |
| LMArena Text: English | 1356 | 1451 | Gemma 4 31B |
| LMArena Text: non-English | 1325 | 1430 | Gemma 4 31B |
| LMArena Text: Chinese | 1371 | 1475 | Gemma 4 31B |
| LMArena Text: German | 1356 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Japanese | 1312 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: Korean | 1306 | Not measured | Only Trinity Large Thinking measured |
| LMArena Text: French | 1366 | 1436 | Gemma 4 31B |
| LMArena Text: Spanish | 1327 | 1442 | Gemma 4 31B |
| LMArena Text: Russian | 1338 | 1460 | Gemma 4 31B |
| LMArena Text: Polish | 1312 | 1433 | Gemma 4 31B |
| LMArena Text: multi-turn | 1320 | 1452 | Gemma 4 31B |
| LMArena Text: longer queries | 1318 | 1446 | Gemma 4 31B |
| LMArena Text: writing and language | 1317 | 1432 | Gemma 4 31B |
| LMArena Text: entertainment and media | 1296 | 1405 | Gemma 4 31B |
| LMArena Vision: English | Not measured | 1271 | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | Not measured | 1326 | Only Gemma 4 31B measured |
| LMArena Vision: reading text | Not measured | 1282 | Only Gemma 4 31B measured |
| LMArena Vision: humor | Not measured | 1280 | Only Gemma 4 31B measured |
| LMArena Vision: captioning | Not measured | 1218 | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | Not measured | 1226 | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | Not measured | 1285 | Only Gemma 4 31B measured |
| LMArena Document | Not measured | 1425 | Only Gemma 4 31B measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Trinity Large Thinking | Gemma 4 31B | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 4 31B costs less
Repository review
50K input + 3K output tokens
Gemma 4 31B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 31B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Arcee AI Trinity Large Thinking | Google Gemma 4 31B |
|---|---|---|
| Maker | Arcee AI | |
| Weights | Open weights | Open weights |
| Released | April 1, 2026 | April 2, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.25 | $0.20 |
| Output $/Mtok | $0.80 | $0.40 |
| Coding index | 5.4 | 38.3 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Trinity Large Thinking better than Gemma 4 31B for coding?
Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 5.4 for Trinity Large Thinking. Pick Trinity Large Thinking when what matters is τ²-Bench Telecom or CaseLaw (Vals AI), where it leads.
Which is cheaper, Trinity Large Thinking or Gemma 4 31B?
Trinity Large Thinking costs $0.25 per million input tokens and $0.80 per million output tokens; Gemma 4 31B costs $0.20 and $0.40. Cost per solved task is known for neither of them.
Which has the bigger context window, Trinity Large Thinking or Gemma 4 31B?
Neither: both take 262K tokens.
How many benchmarks is the Trinity Large Thinking vs Gemma 4 31B comparison based on?
40 benchmarks have a result for both models as of October 21, 2026. Trinity Large Thinking's coding index rests on 1 independent benchmark and Gemma 4 31B's on 2. Where only one model has a result, the page says so instead of naming a winner.