Model comparison
Grok 4.20 Multi-Agent vs Mistral Large
Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 31.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and Mistral Large in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 42.4 to 15.4.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $6 for Mistral Large.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Grok 4.20 Multi-Agent | Mistral Large | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 45.5 | 31.6 |
| Released | 2026-03-09 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 30K | 16K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $2.50 | $6 |
| Results tracked | 20 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 42.4 (#91), Mistral Large: 33.8 (#240)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Coding | 1458 | 1277 |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, Mistral Large: 28.4 (#83)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| LMArena Search | 1204 | — |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 42.4 (#44), Mistral Large: 15.4 (#305)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1257 |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 89.6% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 36.6 (#106), Mistral Large: 17.1 (#285)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Math | 1441 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 39.7 (#116), Mistral Large: 30.0 (#224)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Expert | 1445 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
Grok 4.20 Multi-Agent: 39.8 (#44), Mistral Large: —
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Vision | 1259 | — |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 54.6 (#40), Mistral Large: 40.1 (#214)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Non-English | 1440 | 1237 |
| LMArena Chinese | 1475 | 1240 |
| LMArena French | 1467 | 1324 |
| LMArena German | 1456 | 1254 |
| LMArena Japanese | 1405 | 1187 |
| LMArena Korean | 1416 | 1202 |
| LMArena Russian | 1457 | 1257 |
| LMArena Spanish | 1447 | 1268 |
Instruction Following Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 75.0 (#80), Mistral Large: 68.1 (#186)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1420 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.7 (#84), Mistral Large: 38.3 (#194)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1430 | 1262 |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.1 (#57), Mistral Large: 40.9 (#237)
| Benchmark | Grok 4.20 Multi-Agent | Mistral Large |
|---|---|---|
| LMArena Text | 1450 | 1266 |
| LMArena Creative Writing | 1435 | 1243 |
| LMArena Multi-Turn | 1451 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than Mistral Large?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 31.6 on the Noometry Index.
Which is cheaper, Grok 4.20 Multi-Agent or Mistral Large?
Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Mistral Large lists at $2 and $6.
Is Grok 4.20 Multi-Agent or Mistral Large better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 Multi-Agent does, with 1M tokens against 131K.
How many benchmarks do Grok 4.20 Multi-Agent and Mistral Large share?
17 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Mistral Large has 51.