Model comparison
Gemma 2 9B vs GPT-5.6 Terra
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 25.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and GPT-5.6 Terra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Terra leads 81.6 to 9.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 99.7% for GPT-5.6 Terra.
- Gemma 2 9B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2 9B | GPT-5.6 Terra | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 25.9 | 59.2 |
| Released | 2024-06-24 | 2026-07-09 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $12 |
| Results tracked | 35 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Terra leads
Gemma 2 9B: 29.4 (#304), GPT-5.6 Terra: 57.7 (#19)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| LMArena Coding | 1173 | 1484 |
| DeepSWE | — | 69.6% |
| FrontierCode | — | 41.3% |
| CursorBench | — | 41.3% |
| LMArena WebDev | — | 1522 |
| SciCode | — | 55% |
| WeirdML | — | 78.3% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 1,951 |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, GPT-5.6 Terra: 40.1 (#25)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | — | 58.2% |
| BALROG | — | 53.2% |
| GDP.pdf | — | 24.7% |
| Vending-Bench 2 | — | 7,343 |
Reasoning GPT-5.6 Terra leads
Gemma 2 9B: 15.9 (#309), GPT-5.6 Terra: 60.7 (#21)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1468 |
| Epoch Capabilities Index | 119.83 | 159.62 |
| ARC-AGI-2 | — | 83.9% |
| SimpleBench | — | 48.9% |
| Kagi LLM Benchmark | — | 51.3% |
| NYT Connections (extended) | — | 78.4% |
| ARC-AGI-1 | — | 96.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 54% |
| LiveBench Reasoning | 15.2% | — |
| Mystery Game Puzzles | — | 35% |
| DTBench | — | 93.3% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 55% |
| Surface Evolver Bench | — | 83.8% |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math GPT-5.6 Terra leads
Gemma 2 9B: 9.9 (#318), GPT-5.6 Terra: 81.6 (#12)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 99.7% |
| LMArena Math | 1183 | 1466 |
| FrontierMath (Tiers 1-3) | — | 86% |
| FrontierMath Tier 4 | — | 70.7% |
| ProofBench | — | 74% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge GPT-5.6 Terra leads
Gemma 2 9B: 9.7 (#305), GPT-5.6 Terra: 61.2 (#30)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| GPQA Diamond | 27.5% | 93.3% |
| LMArena Expert | 1147 | 1492 |
| SimpleQA Verified | — | 43.2% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, GPT-5.6 Terra: 47.3 (#11)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | — | 1271 |
| Blueprint-Bench 2 | — | 30.8% |
| Furniture Assembly | — | 54.2% |
| LMArena Document | — | 1472 |
Multilingual GPT-5.6 Terra leads
Gemma 2 9B: 36.6 (#238), GPT-5.6 Terra: 54.4 (#44)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | 1188 | 1439 |
| LMArena Chinese | 1185 | 1513 |
| LMArena French | 1190 | 1471 |
| LMArena German | 1186 | 1460 |
| LMArena Japanese | 1144 | 1457 |
| LMArena Korean | 1137 | 1425 |
| LMArena Russian | 1200 | 1450 |
| LMArena Spanish | 1200 | 1448 |
Instruction Following GPT-5.6 Terra leads
Gemma 2 9B: 57.6 (#269), GPT-5.6 Terra: 76.4 (#40)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | 1178 | 1454 |
| LiveBench Instruction Following | 52.6% | — |
Long Context GPT-5.6 Terra leads
Gemma 2 9B: 36.3 (#233), GPT-5.6 Terra: 44.4 (#68)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | 1197 | 1451 |
Writing & Preference GPT-5.6 Terra leads
Gemma 2 9B: 32.1 (#281), GPT-5.6 Terra: 70.2 (#23)
| Benchmark | Gemma 2 9B | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | 1207 | 1447 |
| LMArena Creative Writing | 1206 | 1410 |
| EQ-Bench Creative Writing | 841 | 1855 |
| LMArena Multi-Turn | 1193 | 1449 |
| EQ-Bench 4 | — | 1234 |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than GPT-5.6 Terra?
GPT-5.6 Terra is the stronger model overall, scoring 59.2 to 25.9 on the Noometry Index.
Is Gemma 2 9B or GPT-5.6 Terra better for coding?
GPT-5.6 Terra scores higher on coding benchmarks: 57.7 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and GPT-5.6 Terra share?
21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-5.6 Terra has 52.