Model comparison
GPT-5.1-Codex-Max vs GPT-5.4
Head-to-head evidence from 13 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.1-Codex-Max #90 (Estimated); GPT-5.4 #8 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.1-Codex-Max and GPT-5.4 share 13 comparable benchmark results. 0 of 8 categories are comparable. 0 results are unique to GPT-5.1-Codex-Max; 39 to GPT-5.4.
Updated July 20, 2026- Shared results
- 13
- GPT-5.1-Codex-Max only
- 0
- GPT-5.4 only
- 39
- Comparable categories
- 0 / 8
Benchmark data for GPT-5.1-Codex-Max and GPT-5.4 is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 13 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
GPT-5.4 is priced at $2.50 input / $15.00 output per 1M tokens, versus $1.25 input / $10.00 output per 1M tokens for GPT-5.1-Codex-Max. GPT-5.4 has the larger context window at 1.05M, compared with 400K for GPT-5.1-Codex-Max.
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 | GPT-5.1-Codex-Max | Δ | GPT-5.4 |
|---|---|---|---|
| Agentic | GPT-5.1-Codex-MaxNot measured | MarginNo overlap | GPT-5.477.2 |
| Coding | GPT-5.1-Codex-MaxNot measured | MarginNo overlap | GPT-5.457.7 |
| Knowledge | GPT-5.1-Codex-MaxNot measured | MarginNo overlap | GPT-5.457.6 |
| Math | GPT-5.1-Codex-MaxNot measured | MarginNo overlap | GPT-5.442.5 |
| Multimodal | GPT-5.1-Codex-MaxNot measured | MarginNo overlap | GPT-5.473.2 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.1-Codex-Max | GPT-5.4 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.1-Codex-Max$1.25 input / $10 output | GPT-5.4$2.5 input / $15 output | GPT-5.1-Codex-Max has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.1-Codex-MaxNot available | GPT-5.474 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.1-Codex-MaxNot available | GPT-5.4151.79 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.1-Codex-Max400K | GPT-5.41.05M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
Agentic17 benchmarks
| Benchmark | GPT-5.1-Codex-Max | GPT-5.4 | Result |
|---|---|---|---|
| τ²-bench resultsSource | 83% | 87.1% | GPT-5.4 leads |
| Terminal-Bench 2.0Source | — | 75.1% | Not comparable |
| CyberGymSource | — | 79.0% | Not comparable |
| BrowseCompSource | — | 82.7% | Not comparable |
| OSWorld-VerifiedSource | — | 75% | Not comparable |
| MCP AtlasSource | — | 70.6% | Not comparable |
| ToolathlonSource | — | 54.6% | Not comparable |
| Claw-EvalSource | — | 60.3% | Not comparable |
| DeepSearchQASource | — | 73.6% | Not comparable |
| AA Agentic IndexSource | — | 41.1% | Not comparable |
| APEX-Agents-AASource | — | 33.3% | Not comparable |
| GDPval-AASource | — | 44.7% | Not comparable |
| GDPval-AASource | — | 1395 | Not comparable |
| Gert LabsSource | — | 64.89% | Not comparable |
| ResearchClawBenchSource | — | 15.3% | Not comparable |
| JobBenchSource | — | 38.9% | Not comparable |
| ExploitGymSource | — | 6.0% | Not comparable |
Coding6 benchmarks
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | GPT-5.1-Codex-Max | GPT-5.4 | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 34.7% | 51.4% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 86.0% | 92.0% | GPT-5.4 leads |
| AA-HLESource | 23.4% | 41.6% | GPT-5.4 leads |
| AA-Omniscience IndexSource | -6.0% | 5.7% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 39.2% | 50.0% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 74.4% | 88.6% | GPT-5.1-Codex-Max leads |
| GPQASource | — | 92.8% | Not comparable |
| HLESource | — | 52.1% | Not comparable |
| HLE w/o toolsSource | — | 39.8% | Not comparable |
| GPQA-DSource | — | 92.8% | Not comparable |
| HealthBench HardSource | — | 40.1% | Not comparable |
| MedXpertQA (Text)Source | — | 59.6% | Not comparable |
| HealthBench ProfessionalSource | — | 48.1% | Not comparable |
Math2 benchmarks
Multimodal11 benchmarks
| Benchmark | GPT-5.1-Codex-Max | GPT-5.4 | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 72.5% | 78.4% | GPT-5.4 leads |
| MMMU-ProSource | — | 81.2% | Not comparable |
| OfficeQA ProSource | — | 53.2% | Not comparable |
| MMMU-Pro w/ PythonSource | — | 82.1% | Not comparable |
| CharXivSource | — | 82.8% | Not comparable |
| ERQASource | — | 65.4% | Not comparable |
| SimpleVQASource | — | 61.1% | Not comparable |
| ScreenSpot ProSource | — | 85.4% | Not comparable |
| ZeroBenchSource | — | 41.0% | Not comparable |
| MedXpertQA (MM)Source | — | 77.1% | Not comparable |
| Design Arena WebsiteSource | — | 1252 | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GPT-5.1-Codex-Max | GPT-5.4 | Result |
|---|---|---|---|
| AA-IFBenchSource | 70.0% | 73.9% | GPT-5.4 leads |
Frequently Asked Questions (3)
Can I compare GPT-5.1-Codex-Max and GPT-5.4 on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for GPT-5.1-Codex-Max and GPT-5.4 today?
GPT-5.1-Codex-Max: $1.25 input / $10.00 output per 1M tokens GPT-5.4: $2.50 input / $15.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.