Model comparison
Gemma 4 31B IT vs Yi-34B
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 27.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Gemma 4 31B IT scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 4 31B IT leads 37.9 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 75.8% for Gemma 4 31B IT and 14.7% for Yi-34B.
Side by side
| Gemma 4 31B IT | Yi-34B | |
|---|---|---|
| Provider | 01.AI | |
| Noometry Index | 43.5 | 27.8 |
| Released | 2026-04-02 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), Yi-34B: 32.3 (#274)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Coding | 1459 | 1112 |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Yi-34B: 21.2 (#226)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1104 |
| Epoch Capabilities Index | 142.74 | 117.39 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| BIG-Bench Hard | — | 71.7% |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Yi-34B: 21.6 (#282)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Math | 1465 | 1114 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#151), Yi-34B: 7.5 (#309)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| GPQA Diamond | 75.8% | 14.7% |
| LMArena Expert | 1465 | 1061 |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| MMLU | — | 76.3% |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Yi-34B: —
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Yi-34B: 29.7 (#264)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Non-English | 1431 | 1079 |
| LMArena Chinese | 1476 | 1176 |
| LMArena French | 1435 | 1081 |
| LMArena Russian | 1460 | 1050 |
| LMArena Spanish | 1444 | 1070 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Yi-34B: 56.2 (#274)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1091 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Yi-34B: 33.2 (#264)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1446 | 1094 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Yi-34B: 34.1 (#273)
| Benchmark | Gemma 4 31B IT | Yi-34B |
|---|---|---|
| LMArena Text | 1443 | 1129 |
| LMArena Creative Writing | 1415 | 1108 |
| LMArena Multi-Turn | 1452 | 1113 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Yi-34B?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 27.8 on the Noometry Index.
Is Gemma 4 31B IT or Yi-34B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 32.3 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and Yi-34B share?
16 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Yi-34B has 23.