- IFBench 52.3
- GPQA-Diamond 76.3
- Mean of Tau2-Airline 88.0 / Tau2-Telecom 94.7 91.3
- PinchBench 91.9
- AIME25 96.3
- BCFLv4 70.1
- MMLU-Pro 83.4
- SWE-bench Verified (mini-swe-agent-v2) 63.2
Trinity Large Thinking
Trinity Large Thinking places in the top three on PinchBench.
Arcee AI Released 1 Apr 2026 22
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Arcee AI Apr 2026 Trinity Large Thinking
Open weights
No Epoch Capabilities Index score yet
- IFBench 52.3% #60 /70
- BFCL V4 70.1% #9 /24
- CritPt 0.86% #98 /160
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU-Pro | 83.4% | #46 of 151 | Model card | |
| LMArena (Elo) | 1,367 | #160 of 333 | Official leaderboard | |
| BullshitBench | 20% | #72 of 107 | Official leaderboard | |
| BullshitBench V2 | 17% | #93 of 122 | Official leaderboard | |
| IFBench | 52.3% | #60 of 70 | Model card | |
| Extended NYT Connections | 16.5% | #85 of 97 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2025 | 96.3% | #19 of 143 | Model card | |
| GPQA Diamond | 76.3% | #131 of 284 | Model card | |
| CritPt | 0.86% | #98 of 160 | Epoch AI | |
| Surface Evolver Bench | 15.6% | #25 of 26 | Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 63.2% | #100 of 150 | Model card | |
| Code Arena | 1,238 | #115 of 124 | Official leaderboard | |
| WebDev Arena | 1,237 | #98 of 105 | Epoch AI | |
| OpenHands Index | 32.1% | #32 of 33 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| tau2-bench | 91.3% | #13 of 69 | Model card | |
| PinchBench | 91.9% | #3 of 13 | Model card | |
| BFCL V4 | 70.1% | #9 of 24 | Model card | |
| PACT | 1,526 | #12 of 26 | Official leaderboard | |
| PinchBench 2.0 | 65.7% | #38 of 57 | Official leaderboard | |
| SnakeBench | 20 | #135 of 183 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CaseLaw v2 | 57.9% | #29 of 53 | Official leaderboard | |
| CorpFin v2 | 54.7% | #86 of 119 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.