Model comparison
Gemma 3 4B vs Mercury
Mercury is the stronger model overall, scoring 37.6 to 28.1 on the Noometry Index.
Last verified . 9 shared benchmarks.
GoogleSummary
- They share 9 benchmarks with published results for both. Gemma 3 4B scores higher in 2 categories and Mercury in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Mercury leads 17.5 to 13.2.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | Mercury | |
|---|---|---|
| Provider | Inception | |
| Noometry Index | 28.1 | 37.6 |
| Released | 2025-03-12 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
Gemma 3 4B: 35.9 (#215), Mercury: 38.7 (#170)
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| LMArena Coding | 1230 | 1322 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Mercury: —
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Mercury leads
Gemma 3 4B: 13.2 (#335), Mercury: 17.5 (#293)
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 21.6% |
| LMArena Hard Prompts | 1253 | 1285 |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Not comparable
Gemma 3 4B: 16.8 (#292), Mercury: —
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| LMArena Math | 1239 | — |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#299), Mercury: —
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
Multilingual Too close to call
Gemma 3 4B: 42.5 (#194), Mercury: 41.6 (#206)
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| LMArena Non-English | 1273 | 1260 |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Too close to call
Gemma 3 4B: 65.2 (#225), Mercury: 65.2 (#224)
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| LMArena Instruction Following | 1239 | 1239 |
Long Context Too close to call
Gemma 3 4B: 38.7 (#194), Mercury: 38.4 (#198)
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| LMArena Longer Query | 1273 | 1266 |
Writing & Preference Mercury leads
Gemma 3 4B: 42.0 (#239), Mercury: 46.2 (#221)
| Benchmark | Gemma 3 4B | Mercury |
|---|---|---|
| LMArena Text | 1291 | 1282 |
| LMArena Creative Writing | 1271 | 1191 |
| LMArena Multi-Turn | 1255 | 1282 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Mercury?
Mercury is the stronger model overall, scoring 37.6 to 28.1 on the Noometry Index.
Is Gemma 3 4B or Mercury better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 35.9 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Mercury share?
9 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mercury has 9.