Model comparison
Command R+ vs Trinity Large Thinking
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 32.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Cohere
Arcee AISummary
- They share 18 benchmarks with published results for both. Command R+ scores higher in 0 categories and Trinity Large Thinking in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Trinity Large Thinking leads 70.5 to 60.0.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $2.50 / $10 for Command R+.
- Trinity Large Thinking accepts more context: 262K tokens versus 128K.
Side by side
| Command R+ | Trinity Large Thinking | |
|---|---|---|
| Provider | Cohere | Arcee AI |
| Noometry Index | 32.4 | 38.6 |
| Released | 2024-08-30 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 80K |
| Input $ / M tokens | $2.50 | $0.25 |
| Output $ / M tokens | $10 | $0.80 |
| Results tracked | 34 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Trinity Large Thinking leads
Command R+: 29.1 (#309), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1187 | 1381 |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Reasoning Trinity Large Thinking leads
Command R+: 9.2 (#344), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1350 |
| SimpleBench | 17.4% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 119.34 | — |
| LiveBench | 31.8% | — |
Math Trinity Large Thinking leads
Command R+: 28.9 (#242), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1188 | 1366 |
| LiveBench Math | 21.3% | — |
Knowledge Trinity Large Thinking leads
Command R+: 36.4 (#169), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 6.9% |
| LMArena Expert | 1174 | 1360 |
| MMLU | 69.4% | — |
Multilingual Trinity Large Thinking leads
Command R+: 38.6 (#227), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1216 | 1325 |
| LMArena Chinese | 1226 | 1373 |
| LMArena French | 1209 | 1374 |
| LMArena German | 1216 | 1356 |
| LMArena Japanese | 1166 | 1311 |
| LMArena Korean | 1138 | 1306 |
| LMArena Russian | 1227 | 1337 |
| LMArena Spanish | 1189 | 1357 |
Instruction Following Trinity Large Thinking leads
Command R+: 60.0 (#254), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1197 | 1334 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Trinity Large Thinking leads
Command R+: 37.3 (#219), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1230 | 1355 |
Writing & Preference Trinity Large Thinking leads
Command R+: 43.5 (#228), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Command R+ | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1229 | 1340 |
| LMArena Creative Writing | 1235 | 1320 |
| LMArena Multi-Turn | 1213 | 1342 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Trinity Large Thinking?
Trinity Large Thinking is the stronger model overall, scoring 38.6 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ 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; Command R+ lists at $2.50 and $10.
Is Command R+ or Trinity Large Thinking better for coding?
Trinity Large Thinking scores higher on coding benchmarks: 34.1 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Trinity Large Thinking does, with 262K tokens against 128K.
How many benchmarks do Command R+ and Trinity Large Thinking share?
18 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Trinity Large Thinking has 24.