# Grok 4.20 vs Grok 4.3

> Side-by-side benchmark comparison for Grok 4.20 and Grok 4.3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/grok-4-20-beta-vs-grok-4-3
- Last updated: September 10, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Grok 4.20 if you want the stronger benchmark profile. Grok 4.3 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Grok 4.20 leads overall 67.13 to 59.73.
- The clearest category separation is in reasoning, where the averages are 34.2 for Grok 4.20 and 65.2 for Grok 4.3.
- The biggest single benchmark swing is Gert Labs in Agentic, with scores of 38.36% and 43.86%.
- Grok 4.3 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Grok 4.20 also has the larger context window at 2M.

## Model Snapshot

| Property | Grok 4.20 | Grok 4.3 |
|----------|----------|----------|
| Creator | xAI | xAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 2M | 1M |
| Overall Score | 67.13 | 59.73 |
| Benchmarks Covered | 23 | 7 |
| Pricing (input/output) | $2.00 / $6.00 | $1.25 / $2.50 |

## Category Breakdown

### Agentic

- Winner: Tie
- Grok 4.20 public-lane score: 26.7 (Supported · #145/152)
- Grok 4.3 public-lane score: 26.9 (Supported · #144/152)

| Benchmark | Grok 4.20 | Grok 4.3 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 47.1% | Coming soon | Coming soon |
| DeepSearchQA | 62.8% | Coming soon | Coming soon |
| Gert Labs | 38.36% | 43.86% | Grok 4.3 |
| Terminal-Bench 2.1 (Vals) | 44.2% | 41.9% | Grok 4.20 |
| ResearchClawBench | Coming soon | 12.4% | Coming soon |

### Coding

- Winner: Grok 4.3
- Grok 4.20 public-lane score: 28.2 (Supported · #141/151)
- Grok 4.3 public-lane score: 33.6 (Supported · #131/151)

| Benchmark | Grok 4.20 | Grok 4.3 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pro | 74.2% | Coming soon | Coming soon |
| SWE-bench Verified | 76.7% | Coming soon | Coming soon |
| SWE-bench Pro | 51.8% | Coming soon | Coming soon |
| Vibe Code Bench | 4.06% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 84.3% | 84.5% | Grok 4.3 |
| SWE-bench (Vals) | 72.2% | 71.4% | Grok 4.20 |

### Multimodal & Grounded

- Winner: Coming soon
- Grok 4.20 public-lane score: 34.6 (#43/48)
- Grok 4.3 public-lane score: 65.6 (#25/48)

| Benchmark | Grok 4.20 | Grok 4.3 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 75.2% | Coming soon | Coming soon |
| CharXiv | 60.9% | Coming soon | Coming soon |
| ERQA | 54.1% | Coming soon | Coming soon |
| SimpleVQA | 57.4% | Coming soon | Coming soon |
| MedXpertQA (MM) | 65.8% | Coming soon | Coming soon |

### Reasoning

- Winner: Coming soon
- Grok 4.20 public-lane score: 34.2 (Unranked · 2 rankable rows)
- Grok 4.3 public-lane score: 65.2 (Unranked · 2 rankable rows)

| Benchmark | Grok 4.20 | Grok 4.3 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 53.3% | Coming soon | Coming soon |
| ARC-AGI-3 | 0.1% | Coming soon | Coming soon |

### Knowledge

- Winner: Grok 4.3
- Grok 4.20 public-lane score: 49.4 (Supported · #85/183)
- Grok 4.3 public-lane score: 57 (Supported · #44/183)

| Benchmark | Grok 4.20 | Grok 4.3 | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 88.5% | Coming soon | Coming soon |
| HLE w/o tools | 31.6% | Coming soon | Coming soon |
| HealthBench Hard | 20.3% | Coming soon | Coming soon |
| MedXpertQA (Text) | 50.2% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 88.6% | 91.4% | Grok 4.3 |
| MMLU-Pro (Vals) | 86.3% | 85.8% | Grok 4.20 |

### Instruction Following

- Winner: Coming soon
- Grok 4.20 public-lane score: Coming soon
- Grok 4.3 public-lane score: 94.4 (#2/123)

## FAQ

### Which is better overall, Grok 4.20 or Grok 4.3?

Grok 4.20 is ahead overall on BenchLM right now.

### Where is the biggest gap between Grok 4.20 and Grok 4.3?

The widest category gap is in reasoning, where the averages are 34.2 for Grok 4.20 and 65.2 for Grok 4.3.

### How many benchmarks does Grok 4.20 cover on BenchLM?

Grok 4.20 currently has 23 sourced benchmark scores on BenchLM.

### How many benchmarks does Grok 4.3 cover on BenchLM?

Grok 4.3 currently has 7 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Grok 4.20 vs Grok 4.20 Multi-agent](/compare/grok-4-20-beta-vs-grok-4-20-multi-agent-beta)
- [Grok 4.3 vs Grok 4.20 Multi-agent](/compare/grok-4-20-multi-agent-beta-vs-grok-4-3)
- [Grok 4.20 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-grok-4-20-beta)
- [Grok 4.3 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-grok-4-3)

## Explore More

- [Grok 4.20 profile](/models/grok-4-20-beta)
- [Grok 4.3 profile](/models/grok-4-3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)