Data points: 79
The readout for GPT-5.3 Codex and Grok 4.20, before the detailed comparison sheet.
Decision read
GPT-5.3 Codex
GPT-5.3 Codex currently has the stronger profile, with verified wins split 4 to 2.
Evidence depth
79 data points
Includes 8 benchmark rows, 0 audit samples, and 8 provider examples.
Selection signal
Start with GPT-5.3 Codex
The charts below split 16 high-signal samples across speed, scores, and audit health.
Model compare GPT-5.3 Codex vs Grok 4.20gpt-5-3-codex-vs-grok-4-20 | Model A GPT-5.3 Codex | Model B Grok 4.20 |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 4 wins | 2 wins |
| Where it leads | Average speed, First-token latency, Provider coverage, Recent tests | Cheapest input price, Free providers |
| Model metadata | GPT-5.3 Codex exposes 400K tokens; notable signals: Text input, Image input, File input, Text output. | Grok 4.20 exposes 2M tokens; notable signals: Text input, Image input, File input, Text output. |
| Developer | OpenAI | No data |
| Context window | 400K tokens | 2M tokens |
| Max output | 128K tokens | No data |
| Released | Feb 2026 | Mar 2026 |
| Modalities | Input TextImageFile Output Text | Input TextImageFile Output Text |
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | No data | No data |
| Tokenizer | GPT | Grok |
| Knowledge cutoff | No data | 2025-09-01 |
| OpenRouter ID | openai/gpt-5.3-codex | x-ai/grok-4.20 |
| References | No data | No data |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
| Metric | GPT-5.3 Codex | Grok 4.20 |
|---|---|---|
| GPQA | 91.5%#4 | 91.1%#6 |
| HLE | 39.9%#5 | 32.2%#12 |
| SciCode | 53.2%#8 | 45.6%#21 |
| Output speed | 77.7 tok/s#66 | 178.5 tok/s#16 |
| Input price | $1.75/M#35 | $2.00/M#36 |
| Output price | $14.00/M#43 | $6.00/M#38 |
| Blended price | $4.81/M#62 | $3.00/M#56 |
| Time to first answer token | 57.06 s#95 | 13.54 s#64 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.3 Codex | Grok 4.20 |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GPT-5.3 Codex | Grok 4.20 |
|---|---|---|
星见雅 API65 tests | GPT-5.3 Codex speed / latency 38 tok/s / 4553ms input / output No data | Grok 4.20 speed / latency 67 tok/s / 1296ms input / output No data |
BUZZ15 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | Grok 4.20 speed / latency 103 tok/s / 9875ms input / output No data |
小水管 API15 tests | GPT-5.3 Codex speed / latency 201 tok/s / 2135ms input / output No data | Grok 4.20 speed / latency 55 tok/s / 1168ms input / output No data |
6345ywz API10 tests | GPT-5.3 Codex speed / latency N/A / N/A input / output No data | Grok 4.20 speed / latency 82 tok/s / 10813ms input / output No data |
6i2 API5 tests | GPT-5.3 Codex speed / latency 89 tok/s / 12856ms input / output No data | Grok 4.20 speed / latency N/A / N/A input / output No data |
GPT-5.3 Codex gpt-5.3-codex-openai-compact speed / latency No data input / output $75.00/M / $600.00/M | Grok 4.20 grok-4.20-beta speed / latency No data input / output $0/M / $0/M | |
GPT-5.3 Codex gpt-5.3-codex speed / latency No data input / output $12.78/M / $102.20/M | Grok 4.20 grok-4.20-fast speed / latency No data input / output $0/M / $0/M | |
GPT-5.3 Codex gpt-5.3-codex-spark speed / latency No data input / output $75.00/M / $600.00/M | Grok 4.20 grok-4.20-fast speed / latency No data input / output $0.0025/M / $0.0025/M |
This report only uses LMSpeed data for GPT-5.3 Codex and Grok 4.20: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | GPT-5.3 Codex | Grok 4.20 |
|---|---|---|
| When to choose each model | GPT-5.3 Codex GPT-5.3 Codex is stronger when you prioritize Average speed, First-token latency, Provider coverage, Recent tests. | Grok 4.20 Grok 4.20 is stronger when you prioritize Cheapest input price, Free providers. |
TL;DR: GPT-5.3 Codex leads across 79 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from GPT-5.3 Codex vs Grok 4.20 into nearby model comparisons with enough verified LMSpeed data.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
