Model comparison
Mercury 2 vs Tulu 3 (Tülu 3) 70B
Mercury 2 is the stronger model overall, scoring 39.1 to 33.0 on the Noometry Index.
Last verified . 10 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. Mercury 2 scores higher in 5 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 25.0.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Inception | Allen Institute for AI (Ai2) |
| Noometry Index | 39.1 | 33.0 |
| Released | 2026-02-20 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 50K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 17 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Mercury 2: 33.5 (#255), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1391 | 1235 |
| LMArena WebDev | 1171 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |
Reasoning Too close to call
Mercury 2: 23.8 (#170), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1220 |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| LMArena Math | — | 1242 |
| MATH Level 5 | — | 42.7% |
Knowledge Mercury 2 leads
Mercury 2: 36.2 (#172), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Vectara Hallucination Rate | 12.3% | — |
| LMArena Expert | 1358 | — |
Multilingual Mercury 2 leads
Mercury 2: 46.6 (#157), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1331 | 1236 |
| LMArena Chinese | 1417 | 1249 |
| LMArena Russian | 1304 | 1246 |
Instruction Following Mercury 2 leads
Mercury 2: 70.2 (#165), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1233 |
Long Context Mercury 2 leads
Mercury 2: 40.5 (#154), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1330 | 1224 |
Writing & Preference Mercury 2 leads
Mercury 2: 53.8 (#155), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Mercury 2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1355 | 1256 |
| LMArena Creative Writing | 1289 | 1231 |
| LMArena Multi-Turn | 1358 | 1252 |
Frequently asked questions
Is Mercury 2 better than Tulu 3 (Tülu 3) 70B?
Mercury 2 is the stronger model overall, scoring 39.1 to 33.0 on the Noometry Index.
Is Mercury 2 or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 33.5 in the Noometry coding category.
How many benchmarks do Mercury 2 and Tulu 3 (Tülu 3) 70B share?
10 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.