Model comparison
Mercury 2.5 vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 33.5 on the Noometry Index. Mercury 2.5 costs 5.7× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Arcee AISummary
- They share 2 benchmarks with published results for both. Mercury 2.5 scores higher in 2 categories and Trinity Large Thinking in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 37.6 to 23.3.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 260K.
- Trinity Large Thinking has downloadable open weights; the other is API-only.
Side by side
| Mercury 2.5 | Trinity Large Thinking | |
|---|---|---|
| Provider | Inception | Arcee AI |
| Noometry Index | 33.5 | 38.6 |
| Released | 2026-09-08 | 2026-04-01 |
| Weights | Proprietary | Open |
| Context window | 260K | 262K |
| Max output | 66K | 80K |
| Input $ / M tokens | $0.04 | $0.25 |
| Output $ / M tokens | $0.15 | $0.80 |
| Results tracked | 4 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2.5 leads
Mercury 2.5: 39.5 (#156), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| SciCode | 38.5% | 36.1% |
| LMArena WebDev | — | 1238 |
| LMArena Coding | — | 1381 |
| ALE-Bench | 301.65 | — |
Reasoning Mercury 2.5 leads
Mercury 2.5: 22.4 (#193), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| CritPt | 0% | 0.9% |
| NYT Connections (extended) | — | 16.5% |
| Thematic Generalization | — | 41.6% |
| LMArena Hard Prompts | — | 1350 |
| Surface Evolver Bench | — | 15.6% |
Math Trinity Large Thinking leads
Mercury 2.5: 23.3 (#272), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| ProofBench | 3% | — |
| LMArena Math | — | 1366 |
Knowledge Not comparable
Mercury 2.5: —, Trinity Large Thinking: 40.9 (#113)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1360 |
Multilingual Not comparable
Mercury 2.5: —, Trinity Large Thinking: 46.2 (#160)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | — | 1325 |
| LMArena Chinese | — | 1373 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1337 |
| LMArena Spanish | — | 1357 |
Instruction Following Not comparable
Mercury 2.5: —, Trinity Large Thinking: 70.5 (#162)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | — | 1334 |
Long Context Not comparable
Mercury 2.5: —, Trinity Large Thinking: 41.3 (#144)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | — | 1355 |
Writing & Preference Not comparable
Mercury 2.5: —, Trinity Large Thinking: 53.8 (#158)
| Benchmark | Mercury 2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1320 |
| LMArena Multi-Turn | — | 1342 |
Frequently asked questions
Is Mercury 2.5 better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 33.5 on the Noometry Index. Mercury 2.5 costs 5.7× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.
Which is cheaper, Mercury 2.5 or Trinity Large Thinking?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is Mercury 2.5 or Trinity Large Thinking better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 260K.
How many benchmarks do Mercury 2.5 and Trinity Large Thinking share?
2 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and Trinity Large Thinking has 24.