Model comparison
Granite 3.0 2b Instruct vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.20 (Non-Reasoning) leads 65.9 to 29.8.
- Granite 3.0 2b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | IBM | xAI |
| Noometry Index | 30.2 | 48.5 |
| Released | — | 2026-02-17 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 13 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 27.8 (#311), Grok 4.20 (Non-Reasoning): 41.8 (#104)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Coding | 1090 | 1458 |
| LMArena WebDev | — | 1374 |
| WeirdML | — | 52.3% |
| BigCodeBench Instruct | 20.5% | — |
| ALE-Bench | — | 1,150 |
Agentic & Tool Use Not comparable
Granite 3.0 2b Instruct: —, Grok 4.20 (Non-Reasoning): 34.3 (#43)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 19.6 (#234), Grok 4.20 (Non-Reasoning): 52.2 (#30)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1451 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| Epoch Capabilities Index | — | 152.01 |
| ForecastBench | — | 61.4 |
Math Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 29.7 (#215), Grok 4.20 (Non-Reasoning): 48.0 (#54)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Math | 1117 | 1455 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | — | 14% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 28.4 (#238), Grok 4.20 (Non-Reasoning): 52.8 (#54)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Expert | 1064 | 1440 |
| GPQA Diamond | — | 89.3% |
| SimpleQA Verified | — | 30.2% |
Multimodal Not comparable
Granite 3.0 2b Instruct: —, Grok 4.20 (Non-Reasoning): 33.2 (#88)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 27.1 (#273), Grok 4.20 (Non-Reasoning): 54.7 (#38)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1033 | 1440 |
| LMArena Chinese | 1070 | 1481 |
| LMArena Russian | 1045 | 1457 |
| LMArena French | — | 1477 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1450 |
| LMArena Korean | — | 1417 |
| LMArena Spanish | — | 1442 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 54.2 (#279), Grok 4.20 (Non-Reasoning): 75.0 (#79)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1056 | 1420 |
Long Context Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 32.5 (#263), Grok 4.20 (Non-Reasoning): 45.4 (#33)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1071 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Granite 3.0 2b Instruct: 29.8 (#287), Grok 4.20 (Non-Reasoning): 65.9 (#42)
| Benchmark | Granite 3.0 2b Instruct | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1080 | 1451 |
| LMArena Creative Writing | 1046 | 1439 |
| LMArena Multi-Turn | 1053 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |
Frequently asked questions
Is Granite 3.0 2b Instruct better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 30.2 on the Noometry Index.
Is Granite 3.0 2b Instruct or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 27.8 in the Noometry coding category.
How many benchmarks do Granite 3.0 2b Instruct and Grok 4.20 (Non-Reasoning) share?
12 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.