Model comparison
Command A vs Tulu 3 (Tülu 3) 70B
Command A is the stronger model overall, scoring 36.5 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Cohere
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Command A scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 14.2.
Side by side
| Command A | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Cohere | Allen Institute for AI (Ai2) |
| Noometry Index | 36.5 | 33.0 |
| Released | 2025-03-13 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Command A: 27.2 (#322), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1330 | 1235 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Command A: 18.3 (#283), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1220 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math Command A leads
Command A: 36.2 (#171), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1300 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Command A leads
Command A: 37.1 (#159), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |
Multilingual Command A leads
Command A: 45.3 (#170), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1313 | 1236 |
| LMArena Chinese | 1327 | 1249 |
| LMArena Russian | 1314 | 1246 |
| LMArena French | 1351 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1285 | — |
| LMArena Korean | 1285 | — |
| LMArena Spanish | 1347 | — |
Instruction Following Command A leads
Command A: 69.1 (#177), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1233 |
Long Context Command A leads
Command A: 40.6 (#151), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1334 | 1224 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Command A | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1331 | 1256 |
| LMArena Creative Writing | 1319 | 1231 |
| LMArena Multi-Turn | 1339 | 1252 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Tulu 3 (Tülu 3) 70B?
Command A is the stronger model overall, scoring 36.5 to 33.0 on the Noometry Index.
Is Command A or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.