Model comparison
Gemma 7B vs Mercury 2
Mercury 2 is the stronger model overall, scoring 38.8 to 29.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
GoogleSummary
- They share 11 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 54.0 to 27.2.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Gemma 7B | Mercury 2 | |
|---|---|---|
| Provider | Inception | |
| Noometry Index | 29.5 | 38.8 |
| Released | 2024-02-21 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 50K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Gemma 7B: 29.9 (#290), Mercury 2: 33.2 (#250)
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Coding | 1048 | 1391 |
| LMArena WebDev | — | 1170 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Mercury 2 leads
Gemma 7B: 19.0 (#247), Mercury 2: 23.0 (#170)
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1362 |
| CritPt | — | 0.8% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.74 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Not comparable
Gemma 7B: 28.7 (#225), Mercury 2: —
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Math | 1066 | — |
| GSM8K | 46.4% | — |
Knowledge Mercury 2 leads
Gemma 7B: 26.8 (#248), Mercury 2: 35.6 (#170)
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Expert | 1002 | 1358 |
| Vectara Hallucination Rate | — | 12.3% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Mercury 2 leads
Gemma 7B: 25.3 (#282), Mercury 2: 46.8 (#153)
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Non-English | 999 | 1331 |
| LMArena Chinese | 1035 | 1416 |
| LMArena Russian | 993 | 1303 |
| LMArena French | 1024 | — |
Instruction Following Mercury 2 leads
Gemma 7B: 51.7 (#290), Mercury 2: 70.4 (#161)
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1328 |
Long Context Mercury 2 leads
Gemma 7B: 31.1 (#277), Mercury 2: 40.4 (#149)
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1022 | 1329 |
Writing & Preference Mercury 2 leads
Gemma 7B: 27.2 (#297), Mercury 2: 54.0 (#151)
| Benchmark | Gemma 7B | Mercury 2 |
|---|---|---|
| LMArena Text | 1056 | 1355 |
| LMArena Creative Writing | 1024 | 1289 |
| LMArena Multi-Turn | 963 | 1358 |
Frequently asked questions
Is Gemma 7B better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 38.8 to 29.5 on the Noometry Index.
Is Gemma 7B or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.2 versus 29.9 in the Noometry coding category.
How many benchmarks do Gemma 7B and Mercury 2 share?
11 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Mercury 2 has 17.