Model comparison
Granite 3.1 2b Instruct vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 33.2 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 0 categories and Mercury 2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 34.1.
- Granite 3.1 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.1 2b Instruct | Mercury 2 | |
|---|---|---|
| Provider | IBM | Inception |
| Noometry Index | 33.2 | 39.1 |
| Released | — | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 12 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 3.1 2b Instruct: 33.4 (#257), Mercury 2: 33.5 (#255)
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Coding | 1149 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |
Reasoning Mercury 2 leads
Granite 3.1 2b Instruct: 22.0 (#209), Mercury 2: 23.8 (#170)
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1362 |
| CritPt | — | 0.8% |
Math Not comparable
Granite 3.1 2b Instruct: 33.1 (#206), Mercury 2: —
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Math | 1159 | — |
Knowledge Mercury 2 leads
Granite 3.1 2b Instruct: 30.8 (#224), Mercury 2: 36.2 (#172)
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Expert | 1131 | 1358 |
| Vectara Hallucination Rate | — | 12.3% |
Multilingual Mercury 2 leads
Granite 3.1 2b Instruct: 29.1 (#269), Mercury 2: 46.6 (#157)
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1068 | 1331 |
| LMArena Chinese | 1139 | 1417 |
| LMArena Russian | 1063 | 1304 |
Instruction Following Mercury 2 leads
Granite 3.1 2b Instruct: 57.7 (#264), Mercury 2: 70.2 (#165)
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1329 |
Long Context Mercury 2 leads
Granite 3.1 2b Instruct: 35.0 (#244), Mercury 2: 40.5 (#154)
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1155 | 1330 |
Writing & Preference Mercury 2 leads
Granite 3.1 2b Instruct: 34.1 (#274), Mercury 2: 53.8 (#155)
| Benchmark | Granite 3.1 2b Instruct | Mercury 2 |
|---|---|---|
| LMArena Text | 1127 | 1355 |
| LMArena Creative Writing | 1116 | 1289 |
| LMArena Multi-Turn | 1099 | 1358 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or Mercury 2 better for coding?
They score almost the same on coding (33.4 vs 33.5); test both on your own repository before choosing.
How many benchmarks do Granite 3.1 2b Instruct and Mercury 2 share?
11 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Mercury 2 has 17.