Model comparison
Grok 4.20 Multi-Agent vs o4-mini
Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 41.6 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 5 categories and o4-mini in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 42.4 to 24.6.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 200K.
Side by side
| Grok 4.20 Multi-Agent | o4-mini | |
|---|---|---|
| Provider | xAI | OpenAI |
| Noometry Index | 45.5 | 41.6 |
| Released | 2026-03-09 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 30K | 100K |
| Input $ / M tokens | $1.25 | $1.10 |
| Output $ / M tokens | $2.50 | $4.40 |
| Results tracked | 20 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 4.20 Multi-Agent: 42.4 (#91), o4-mini: 41.6 (#110)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Coding | 1458 | 1369 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, o4-mini: 32.3 (#57)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| LMArena Search | 1204 | — |
| METR Time Horizons | — | 63.9% |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 42.4 (#44), o4-mini: 24.6 (#143)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1351 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LMCA | — | 26.5% |
| Epoch Capabilities Index | — | 145.63 |
| ForecastBench | — | 61.8 |
Math o4-mini leads
Grok 4.20 Multi-Agent: 36.6 (#106), o4-mini: 40.2 (#79)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Math | 1441 | 1390 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| Omni-MATH | — | 72% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Grok 4.20 Multi-Agent: 39.7 (#116), o4-mini: 43.5 (#83)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Expert | 1445 | 1344 |
| GPQA Diamond | — | 79.6% |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Confabulations | — | 15.8% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
Multimodal Too close to call
Grok 4.20 Multi-Agent: 39.8 (#44), o4-mini: 39.5 (#46)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Vision | 1259 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 54.6 (#40), o4-mini: 47.2 (#149)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Non-English | 1440 | 1336 |
| LMArena Chinese | 1475 | 1355 |
| LMArena French | 1467 | 1362 |
| LMArena German | 1456 | 1336 |
| LMArena Japanese | 1405 | 1308 |
| LMArena Korean | 1416 | 1313 |
| LMArena Russian | 1457 | 1334 |
| LMArena Spanish | 1447 | 1346 |
Instruction Following Too close to call
Grok 4.20 Multi-Agent: 75.0 (#80), o4-mini: 75.4 (#63)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1420 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
Grok 4.20 Multi-Agent: 43.7 (#84), o4-mini: 45.5 (#31)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Longer Query | 1430 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.1 (#57), o4-mini: 54.2 (#148)
| Benchmark | Grok 4.20 Multi-Agent | o4-mini |
|---|---|---|
| LMArena Text | 1450 | 1353 |
| LMArena Creative Writing | 1435 | 1294 |
| LMArena Multi-Turn | 1451 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than o4-mini?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 41.6 on the Noometry Index.
Which is cheaper, Grok 4.20 Multi-Agent or o4-mini?
Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Grok 4.20 Multi-Agent or o4-mini better for coding?
They score almost the same on coding (42.4 vs 41.6); test both on your own repository before choosing.
Which has the bigger context window?
Grok 4.20 Multi-Agent does, with 1M tokens against 200K.
How many benchmarks do Grok 4.20 Multi-Agent and o4-mini share?
18 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and o4-mini has 60.