Model comparison
GPT-4.1 vs GPT-5.1-Codex-Max
Head-to-head evidence from 12 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-4.1 #111 (Supported); GPT-5.1-Codex-Max #95 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-4.1 and GPT-5.1-Codex-Max share 12 comparable benchmark results. 0 of 8 categories are comparable. 8 results are unique to GPT-4.1; 1 to GPT-5.1-Codex-Max.
Updated July 24, 2026- Shared results
- 12
- GPT-4.1 only
- 8
- GPT-5.1-Codex-Max only
- 1
- Comparable categories
- 0 / 8
Benchmark data for GPT-4.1 and GPT-5.1-Codex-Max is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 12 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-5.1-Codex-Max is priced at $1.25 input / $10.00 output per 1M tokens, versus $2.00 input / $8.00 output per 1M tokens for GPT-4.1. GPT-4.1 has the larger context window at 1M, 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-4.1 | Δ | GPT-5.1-Codex-Max |
|---|---|---|---|
| Coding | GPT-4.154.6 | MarginNo overlap | GPT-5.1-Codex-MaxNot measured |
| Knowledge | GPT-4.166.3 | MarginNo overlap | GPT-5.1-Codex-MaxNot measured |
| Math | GPT-4.14.1 | MarginNo overlap | GPT-5.1-Codex-MaxNot measured |
| Inst. Following | GPT-4.187.4 | MarginNo overlap | GPT-5.1-Codex-MaxNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-4.1 | GPT-5.1-Codex-Max | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-4.1$2 input / $8 output | GPT-5.1-Codex-Max$1.25 input / $10 output | GPT-4.1 has the lower combined listed price. |
| Generation speedtokens per second | GPT-4.1108 tok/s | GPT-5.1-Codex-MaxNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-4.11.02 s | GPT-5.1-Codex-MaxNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-4.11M | GPT-5.1-Codex-Max400K | GPT-4.1 lists the larger context window. |
Benchmark Deep Dive
Agentic2 benchmarks
Coding3 benchmarks
Reasoning2 benchmarks
Knowledge8 benchmarks
| Benchmark | GPT-4.1 | GPT-5.1-Codex-Max | Result |
|---|---|---|---|
| MMLUSource | 90.2% | — | Not comparable |
| GPQASource | 66.3% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 19.4% | 34.7% | GPT-5.1-Codex-Max leads |
| AA-GPQA DiamondSource | 66.6% | 86.0% | GPT-5.1-Codex-Max leads |
| AA-HLESource | 4.6% | 23.4% | GPT-5.1-Codex-Max leads |
| AA-Omniscience IndexSource | -36.2% | -6.0% | GPT-5.1-Codex-Max leads |
| AA-Omniscience AccuracySource | 24.2% | 39.2% | GPT-5.1-Codex-Max leads |
| AA-Omniscience Hallucination RateSource | 79.6% | 74.4% | GPT-5.1-Codex-Max leads |
Math2 benchmarks
Multimodal2 benchmarks
Frequently Asked Questions (3)
Can I compare GPT-4.1 and GPT-5.1-Codex-Max 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-4.1 and GPT-5.1-Codex-Max today?
GPT-4.1: $2.00 input / $8.00 output per 1M tokens GPT-5.1-Codex-Max: $1.25 input / $10.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.