Model comparison
GPT-5.1 vs Grok 4.20 Multi-Agent
GPT-5.1 is the stronger model overall, scoring 48.8 to 45.5 on the Noometry Index. Grok 4.20 Multi-Agent costs 2.2× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. GPT-5.1 scores higher in 7 categories and Grok 4.20 Multi-Agent in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.1 leads 50.3 to 36.6.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.1 | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 48.8 | 45.5 |
| Released | 2025-11-13 | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $1.25 | $1.25 |
| Output $ / M tokens | $10 | $2.50 |
| Results tracked | 63 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.9 (#59), Grok 4.20 Multi-Agent: 42.4 (#91)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1454 | 1458 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| WeirdML | 60.8% | — |
| LiveBench Coding | 72.5% | — |
| ALE-Bench | 1,192 | — |
Agentic & Tool Use Not comparable
GPT-5.1: 32.5 (#55), Grok 4.20 Multi-Agent: —
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | 1199 | 1204 |
| Terminal-Bench | 47.6% | — |
| DeepResearch Bench | 42.8% | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning Grok 4.20 Multi-Agent leads
GPT-5.1: 39.9 (#50), Grok 4.20 Multi-Agent: 42.4 (#44)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1448 |
| ARC-AGI-2 | 17.6% | — |
| SimpleBench | 53.2% | — |
| NYT Connections (extended) | — | 89.6% |
| ARC-AGI-1 | 72.8% | — |
| CritPt | 4.9% | — |
| Chess Puzzles | 32% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| Epoch Capabilities Index | 149.66 | — |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 50.3 (#45), Grok 4.20 Multi-Agent: 36.6 (#106)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1446 | 1441 |
| OTIS Mock AIME 2024-2025 | 88.6% | — |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5.1 leads
GPT-5.1: 50.5 (#65), Grok 4.20 Multi-Agent: 39.7 (#116)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1470 | 1445 |
| GPQA Diamond | 87.6% | — |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| MMLU-Pro | 57.9% | — |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.0 (#17), Grok 4.20 Multi-Agent: 39.8 (#44)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 1250 | 1259 |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual Too close to call
GPT-5.1: 54.0 (#51), Grok 4.20 Multi-Agent: 54.6 (#40)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1431 | 1440 |
| LMArena Chinese | 1495 | 1475 |
| LMArena French | 1451 | 1467 |
| LMArena German | 1439 | 1456 |
| LMArena Japanese | 1453 | 1405 |
| LMArena Korean | 1401 | 1416 |
| LMArena Russian | 1435 | 1457 |
| LMArena Spanish | 1430 | 1447 |
Instruction Following GPT-5.1 leads
GPT-5.1: 84.0 (#1), Grok 4.20 Multi-Agent: 75.0 (#80)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1442 | 1420 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Grok 4.20 Multi-Agent: 43.7 (#84)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1448 | 1430 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference Too close to call
GPT-5.1: 64.7 (#53), Grok 4.20 Multi-Agent: 64.1 (#57)
| Benchmark | GPT-5.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1443 | 1450 |
| LMArena Creative Writing | 1427 | 1435 |
| LMArena Multi-Turn | 1449 | 1451 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Grok 4.20 Multi-Agent?
GPT-5.1 is the stronger model overall, scoring 48.8 to 45.5 on the Noometry Index. Grok 4.20 Multi-Agent costs 2.2× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 or Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Grok 4.20 Multi-Agent better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.9 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 Multi-Agent does, with 1M tokens against 400K.
How many benchmarks do GPT-5.1 and Grok 4.20 Multi-Agent share?
19 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Grok 4.20 Multi-Agent has 20.