Gemma 4 31B vs Mercury 2
Updated October 21, 2026. 34 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 0.0 for Mercury 2.
Pick Mercury 2 when the benchmark that matters is τ²-Bench Telecom, where it leads.
- Shared results
- 34
- Gemma 4 31B only
- 34
- Mercury 2 only
- 8
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Gemma 4 31B
Gemma 4 31B scores 38.3 against 0.0.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemma 4 31B
Gemma 4 31B leads, 14.7 against 10.8.
Same board, both measured
Agentic work
AA Agentic Index
Gemma 4 31B
Gemma 4 31B leads, 4.2 against 1.6.
Same board, both measured
Web design
Design Arena: websites
No call
Only Mercury 2 has a Design Arena: websites result, 1036.
Directional only
Long documents
Listed context window
Gemma 4 31B
Gemma 4 31B takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
Gemma 4 31B $0.0004, Mercury 2 $0.0006 per turn.
List prices
At a glance
- Coding index
- Gemma 4 31B 38.3 from 2 benchmarks, Mercury 2 0.0 from 1 benchmark.
- Widest category
- General, 17.2 points apart on average over 13 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: Gemma 4 31B 1359 against Mercury 2 1160, 33.3 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 31B $0.40 against Mercury 2 $0.75 per million output tokens, 1.9x apart.
- Context window
- Gemma 4 31B takes 262K tokens, Mercury 2 128K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemma 4 31B | Bars | Mercury 2 | Ties |
|---|---|---|---|---|
| Coding | 10 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 5 | 0 | ||
| Knowledge | 3 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 33 | 1 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index100
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| LiveBench coding | 49.0% | Not measured | Only Gemma 4 31B measured |
| LMArena WebDev | 1367 | 1171 | Gemma 4 31B |
| AA Coding Index | 43.4 | 31.1 | Gemma 4 31B |
| SciCode | 45.5% | 37.7% | Gemma 4 31B |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | 26.5% | Gemma 4 31B |
| WeirdML | 52.3% | 43.2% | Gemma 4 31B |
| ALE-Bench | 925.5 | 785.6 | Gemma 4 31B |
| LMArena Text: coding | 1459 | 1390 | Gemma 4 31B |
| LMArena Text: software and IT | 1463 | 1385 | Gemma 4 31B |
| LMArena WebDev: React | 1359 | 1160 | Gemma 4 31B |
| LMArena WebDev: HTML | 1380 | 1199 | Gemma 4 31B |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.7 | 10.8 | Gemma 4 31B |
| Epoch Capabilities Index | 143.0 | Not measured | Only Gemma 4 31B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| AA Agentic Index | 4.2 | 1.6 | Gemma 4 31B |
| LiveBench research | 44.4% | Not measured | Only Gemma 4 31B measured |
| LiveBench browser | 4.0% | Not measured | Only Gemma 4 31B measured |
| LiveBench long agentic | 13.3% | Not measured | Only Gemma 4 31B measured |
| τ²-Bench Telecom | 65.5% | 70.8% | Mercury 2 |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| LiveBench reasoning | 68.3% | Not measured | Only Gemma 4 31B measured |
| GPQA Diamond (Artificial Analysis run) | 85.7% | 77.0% | Gemma 4 31B |
| Humanity's Last Exam (Artificial Analysis run) | 23.6% | 17.1% | Gemma 4 31B |
| GPQA Diamond (Epoch AI run) | 75.8% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: hard prompts | 1448 | 1362 | Gemma 4 31B |
| LMArena Text: expert | 1464 | 1358 | Gemma 4 31B |
| LMArena Text: hard prompts in English | 1456 | 1374 | Gemma 4 31B |
| LMArena Vision: diagrams | 1283 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: homework | 1310 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 12 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 73.3% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: math | 1463 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: mathematical work | 1465 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | 52.6% | Not measured | Only Gemma 4 31B measured |
| MortgageTax (Vals AI) | 61.4% | Not measured | Only Gemma 4 31B measured |
| SimpleQA Verified | 10.4% | Not measured | Only Gemma 4 31B measured |
| LMArena Text: science | 1457 | 1343 | Gemma 4 31B |
| LMArena Text: medicine and healthcare | 1451 | 1363 | Gemma 4 31B |
| LMArena Text: legal and government | 1438 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: business and finance | 1430 | 1349 | Gemma 4 31B |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1036 | Only Mercury 2 measured |
| Design Arena: UI components | Not measured | 998 | Only Mercury 2 measured |
| Design Arena: game dev | Not measured | 985 | Only Mercury 2 measured |
| Design Arena: data viz | Not measured | 1009 | Only Mercury 2 measured |
| Design Arena: 3D | Not measured | 982 | Only Mercury 2 measured |
| Design Arena: all code categories | Not measured | 1022 | Only Mercury 2 measured |
| Design Arena: SVG | Not measured | 998 | Only Mercury 2 measured |
| Design Arena: ASCII art | Not measured | 990 | Only Mercury 2 measured |
| LiveBench design | 58.4% | Not measured | Only Gemma 4 31B measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| LiveBench data analysis | 53.3% | Not measured | Only Gemma 4 31B measured |
| SAGE (Vals AI) | 55.0% | Not measured | Only Gemma 4 31B measured |
| IFBench | 75.6% | 69.8% | Gemma 4 31B |
| Long context reasoning (AA-LCR) | 69.7% | 43.7% | Gemma 4 31B |
| DTBench | 82.7% | Not measured | Only Gemma 4 31B measured |
| LMCA | 39.3% | Not measured | Only Gemma 4 31B measured |
| Surface Evolver Bench | 30.6% | Not measured | Only Gemma 4 31B measured |
| LMArena Text | 1443 | 1354 | Gemma 4 31B |
| LMArena Text: instruction following | 1433 | 1328 | Gemma 4 31B |
| LMArena Text: creative writing | 1417 | 1286 | Gemma 4 31B |
| LMArena Vision | 1276 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: English | 1451 | 1378 | Gemma 4 31B |
| LMArena Text: non-English | 1430 | 1330 | Gemma 4 31B |
| LMArena Text: Chinese | 1475 | 1414 | Gemma 4 31B |
| LMArena Text: French | 1436 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Spanish | 1442 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: Russian | 1460 | 1304 | Gemma 4 31B |
| LMArena Text: Polish | 1433 | Not measured | Only Gemma 4 31B measured |
| LMArena Text: multi-turn | 1452 | 1357 | Gemma 4 31B |
| LMArena Text: longer queries | 1446 | 1329 | Gemma 4 31B |
| LMArena Text: writing and language | 1432 | 1300 | Gemma 4 31B |
| LMArena Text: entertainment and media | 1405 | 1314 | Gemma 4 31B |
| LMArena Vision: English | 1271 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | 1326 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: reading text | 1282 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: humor | 1280 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: captioning | 1218 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | 1226 | Not measured | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | 1285 | Not measured | Only Gemma 4 31B measured |
| LMArena Document | 1425 | Not measured | Only Gemma 4 31B measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 31B | Mercury 2 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 4 31B costs less
Repository review
50K input + 3K output tokens
Gemma 4 31B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 31B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemma 4 31B | Inception Mercury 2 |
|---|---|---|
| Maker | Inception | |
| Weights | Open weights | No public weights listed |
| Released | April 2, 2026 | March 4, 2026 |
| Context window | 262K | 128K |
| Input $/Mtok | $0.20 | $0.25 |
| Output $/Mtok | $0.40 | $0.75 |
| Coding index | 38.3 | 0.0 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 31B better than Mercury 2 for coding?
Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 0.0 for Mercury 2. Pick Mercury 2 when the benchmark that matters is τ²-Bench Telecom, where it leads.
Which is cheaper, Gemma 4 31B or Mercury 2?
Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens; Mercury 2 costs $0.25 and $0.75. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 4 31B or Mercury 2?
Gemma 4 31B, with 262K tokens against 128K.
How many benchmarks is the Gemma 4 31B vs Mercury 2 comparison based on?
34 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and Mercury 2's on 1. Where only one model has a result, the page says so instead of naming a winner.