Model comparison
Grok 4.6 vs Trinity Large Thinking
Grok 4.6 is the stronger model overall, scoring 56.9 to 38.6 on the Noometry Index. Trinity Large Thinking costs 7.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Arcee AISummary
- They share 21 benchmarks with published results for both. Grok 4.6 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 Grok 4.6 leads 61.4 to 16.9.
- The biggest single-benchmark swing is NYT Connections (extended): 80% for Grok 4.6 and 16.5% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 262K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | Trinity Large Thinking | |
|---|---|---|
| Provider | xAI | Arcee AI |
| Noometry Index | 56.9 | 38.6 |
| Released | 2026-08-12 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 500K | 262K |
| Max output | 500K | 80K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $6 | $0.80 |
| Results tracked | 49 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.5 (#16), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1617 | 1238 |
| SciCode | 56.5% | 36.1% |
| LMArena Coding | 1465 | 1381 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
| WeirdML | 67.3% | — |
| ALE-Bench | 1,508 | — |
Agentic & Tool Use Not comparable
Grok 4.6: 39.4 (#27), Trinity Large Thinking: —
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 65.3% | — |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 80% | 16.5% |
| CritPt | 19.7% | 0.9% |
| LMArena Hard Prompts | 1447 | 1350 |
| ARC-AGI-2 | 67.1% | — |
| SimpleBench | 75.9% | — |
| ARC-AGI-1 | 87.5% | — |
| Chess Puzzles | 40% | — |
| Thematic Generalization | — | 41.6% |
| EBR-Bench | 30.5% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.3% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 156.44 | — |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1423 | 1366 |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 31.7% | — |
| OTIS Mock AIME 2024-2025 | 99.2% | — |
| ProofBench | 51% | — |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1467 | 1360 |
| GPQA Diamond | 94% | — |
| SimpleQA Verified | 49.3% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
Grok 4.6: 43.6 (#23), Trinity Large Thinking: —
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.0 (#74), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1420 | 1325 |
| LMArena Chinese | 1480 | 1373 |
| LMArena French | 1461 | 1374 |
| LMArena German | 1431 | 1356 |
| LMArena Japanese | 1376 | 1311 |
| LMArena Korean | 1397 | 1306 |
| LMArena Russian | 1422 | 1337 |
| LMArena Spanish | 1404 | 1357 |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.4 (#63), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1431 | 1334 |
Long Context Grok 4.6 leads
Grok 4.6: 44.5 (#66), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1454 | 1355 |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Grok 4.6 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1428 | 1340 |
| LMArena Creative Writing | 1428 | 1320 |
| LMArena Multi-Turn | 1425 | 1342 |
Frequently asked questions
Is Grok 4.6 better than Trinity Large Thinking?
Grok 4.6 is the stronger model overall, scoring 56.9 to 38.6 on the Noometry Index. Trinity Large Thinking costs 7.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Grok 4.6 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; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or Trinity Large Thinking better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 262K.
How many benchmarks do Grok 4.6 and Trinity Large Thinking share?
21 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Trinity Large Thinking has 24.