Data points: 69
Model compare
The readout for GPT-4 and GPT-5.1 Codex, before the detailed comparison sheet.
Weighted outcome: GPT-5.1 Codex. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GPT-5.1 Codex
GPT-5.1 Codex has the higher weighted result; Model A / B score 6.7 to 93.3.
Evidence depth
69 data points
Includes 3 benchmark rows, 0 audit samples, and 6 provider examples.
Selection signal
Start with GPT-5.1 Codex
The charts below split 9 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for GPT-4 and GPT-5.1 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GPT-4 | GPT-5.1 Codex |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 6.7 pts | 93.3 pts |
| Benchmark category leads | 0 categories | 1 categories |
| Operational advantages | Free providers | Cheapest input price, Provider coverage |
| Context window | 8.2K tokens | 400K tokens |
| Max output | 4.1K tokens | 128K tokens |
| Modalities | Input Text Output Text | Input Text |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | GPT-4 | GPT-5.1 Codex |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | May 2023 | Nov 2025 |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | 2021-09-30 | No data |
| OpenRouter ID | openai/gpt-4 | openai/gpt-5.1-codex |
| References | No data | No data |
This report only uses LMSpeed data for GPT-4 and GPT-5.1 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
GPT-4
GPT-4 has these operational advantages: Free providers.
GPT-5.1 Codex
GPT-5.1 Codex is stronger in benchmark categories (Coding) and operational dimensions (Cheapest input price, Provider coverage).
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
GPT-4
49.5
Avg. score
GPT-5.1 Codex
52.4
GPT-5.1 Codex
GPT-5.1 Codex leads by 1.2
GPT-5.1 Codex
GPT-5.1 Codex
GPT-5.1 Codex
No data
No data
GPT-5.1 Codex
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-4
$30.00/M
Rank #160/162 · confidence 4
GPT-5.1 Codex
winner$1.25/M
Rank #107/162 · confidence 4
GPT-4
$37.50/M
Rank #160/162 · confidence 4
GPT-5.1 Codex
winner$3.44/M
Rank #117/162 · confidence 4
GPT-4
$60.00/M
Rank #155/162 · confidence 4
GPT-5.1 Codex
winner$10.00/M
Rank #120/162 · confidence 4
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-4 | GPT-5.1 Codex |
|---|---|---|
| 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-4 | GPT-5.1 Codex |
|---|---|---|
0 tests | GPT-4 speed / latency N/A / N/A input / output No data | GPT-5.1 Codex speed / latency N/A / N/A input / output No data |
0 tests | GPT-4 speed / latency N/A / N/A input / output No data | GPT-5.1 Codex speed / latency N/A / N/A input / output No data |
0 tests | GPT-4 speed / latency N/A / N/A input / output No data | GPT-5.1 Codex speed / latency N/A / N/A input / output No data |
0 tests | GPT-4 speed / latency N/A / N/A input / output No data | GPT-5.1 Codex speed / latency N/A / N/A input / output No data |
0 tests | GPT-4 speed / latency N/A / N/A input / output No data | GPT-5.1 Codex speed / latency N/A / N/A input / output No data |
GPT-4 gpt-4-0314 speed / latency No data input / output $0/request | GPT-5.1 Codex gpt-5.1-codex speed / latency No data input / output $0/request |
Weighted outcome: GPT-5.1 Codex. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Output
| Features | Text inputText outputTool callingStructured outputsJSON mode | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
