Model comparison
Grok 4.20 vs Step 3.7 Flash
Head-to-head evidence from 6 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
BenchAlign evidence: Grok 4.20 estimated; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Grok 4.20 and Step 3.7 Flash share 6 comparable benchmark results. 2 of 8 categories are comparable. 13 results are unique to Grok 4.20; 24 to Step 3.7 Flash.
Updated July 16, 2026- Shared results
- 6
- Grok 4.20 only
- 13
- Step 3.7 Flash only
- 24
- Comparable categories
- 2 / 8
Pick Grok 4.20 if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if agentic is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 6 shared benchmark results across 3 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Grok 4.20 is clearly ahead on the provisional aggregate, 68 to 57. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Grok 4.20's sharpest advantage is in coding, where it averages 67.1 against 56.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 47.1% to 59.5%. Step 3.7 Flash does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Grok 4.20 is also the more expensive model on tokens at $2.00 input / $6.00 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 5.2x on output cost alone. Grok 4.20 gives you the larger context window at 2M, compared with 256K for Step 3.7 Flash.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Grok 4.20 | Δ | Step 3.7 Flash |
|---|---|---|---|
| Agentic | Grok 4.2047.1 | Margin→ 19.3 | Step 3.7 Flash66.4 |
| Coding | Grok 4.2067.1 | Margin← 10.8 | Step 3.7 Flash56.3 |
| Reasoning | Grok 4.2053.3 | MarginNo overlap | Step 3.7 FlashNot measured |
| Multimodal | Grok 4.2070.1 | MarginNo overlap | Step 3.7 FlashNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 47.1%B 59.5%Winner: Step 3.7 FlashΔ 12.4Terminal-Bench 2.0: Grok 4.20 scored 47.1%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 51.8%B 56.3%Winner: Step 3.7 FlashΔ 4.5SWE-bench Pro: Grok 4.20 scored 51.8%; Step 3.7 Flash scored 56.3%. Step 3.7 Flash wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Grok 4.20 | Step 3.7 Flash | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Grok 4.20$2 input / $6 output | Step 3.7 Flash$0.2 input / $1.15 output | Step 3.7 Flash has the lower combined listed price. |
| Generation speedtokens per second | Grok 4.20233 tok/s | Step 3.7 FlashNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Grok 4.2010.33 s | Step 3.7 FlashNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Grok 4.202M | Step 3.7 Flash256K | Grok 4.20 lists the larger context window. |
Benchmark Deep Dive
AgenticStep 3.7 Flash wins12 benchmarks
| Benchmark | Grok 4.20 | Step 3.7 Flash | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 47.1% | 59.5% | Step 3.7 Flash leads |
| DeepSearchQASource | 62.8% | 92.8% | Step 3.7 Flash leads |
| Gert LabsSource | 38.36% | 51.57% | Step 3.7 Flash leads |
| BrowseCompSource | — | 75.8% | Not comparable |
| GDPval-AASource | — | 25.9% | Not comparable |
| ToolathlonSource | — | 49.5% | Not comparable |
| Claw-EvalSource | — | 67.1% | Not comparable |
| HLE w/ toolsSource | — | 47.2% | Not comparable |
| AA Agentic IndexSource | — | 21.5% | Not comparable |
| τ²-bench resultsSource | — | 98.5% | Not comparable |
| GDPval-AASource | — | 1017 | Not comparable |
| APEX-Agents-AASource | — | 14.8% | Not comparable |
CodingGrok 4.20 wins8 benchmarks
| Benchmark | Grok 4.20 | Step 3.7 Flash | Result |
|---|---|---|---|
| LiveCodeBench ProSource | 74.2% | — | Not comparable |
| SWE-bench VerifiedSource | 76.7% | — | Not comparable |
| SWE-bench ProSource | 51.8% | 56.3% | Step 3.7 Flash leads |
| Vibe Code BenchSource | 4.06% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 59.5% | Not comparable |
| AA Coding IndexSource | — | 39.6% | Not comparable |
| Terminal-Bench HardSource | — | 35.6% | Not comparable |
| AA-SciCodeSource | — | 40.0% | Not comparable |
Reasoning3 benchmarks
Knowledge10 benchmarks
| Benchmark | Grok 4.20 | Step 3.7 Flash | Result |
|---|---|---|---|
| GPQA-DSource | 88.5% | — | Not comparable |
| HLE w/o toolsSource | 31.6% | — | Not comparable |
| HealthBench HardSource | 20.3% | — | Not comparable |
| MedXpertQA (Text)Source | 50.2% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 30.3% | Not comparable |
| AA-GPQA DiamondSource | — | 80.9% | Not comparable |
| AA-HLESource | — | 19.9% | Not comparable |
| AA-Omniscience IndexSource | — | -37.5% | Not comparable |
| AA-Omniscience AccuracySource | — | 25.4% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 84.4% | Not comparable |
Multimodal9 benchmarks
| Benchmark | Grok 4.20 | Step 3.7 Flash | Result |
|---|---|---|---|
| MMMU-ProSource | 75.2% | — | Not comparable |
| CharXivSource | 60.9% | — | Not comparable |
| ERQASource | 54.1% | — | Not comparable |
| SimpleVQASource | 57.4% | 79.2% | Step 3.7 Flash leads |
| MedXpertQA (MM)Source | 65.8% | — | Not comparable |
| GDPval-AASource | 1055 | — | Not comparable |
| Design Arena WebsiteSource | 1262 | 1218 | Grok 4.20 leads |
| V*Source | — | 95.3% | Not comparable |
| AA-MMMU-ProSource | — | 75.3% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Grok 4.20 | Step 3.7 Flash | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 67.3% | Not comparable |
Frequently Asked Questions (3)
Which is better, Grok 4.20 or Step 3.7 Flash?
Grok 4.20 is ahead on BenchLM's provisional leaderboard, 68 to 57. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 47.1% and 59.5%.
Which is better for coding, Grok 4.20 or Step 3.7 Flash?
Grok 4.20 has the edge for coding in this comparison, averaging 67.1 versus 56.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Grok 4.20 or Step 3.7 Flash?
Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 47.1. Inside this category, DeepSearchQA is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.