Skip to main content

Model comparison

GPT-5.1-Codex-Max vs Phi-4

Data verified

Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

53.72/100
Margin
31.4pts
← winning
Microsoft
22.32/100
0 category wins0 category wins

Public leaderboard positions: GPT-5.1-Codex-Max #95 (Estimated); Phi-4 #202 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.1-Codex-Max and Phi-4 share 11 comparable benchmark results. 0 of 8 categories are comparable. 2 results are unique to GPT-5.1-Codex-Max; 0 to Phi-4.

Updated July 24, 2026
Shared results
11
GPT-5.1-Codex-Max only
2
Phi-4 only
0
Comparable categories
0 / 8

Benchmark data for GPT-5.1-Codex-Max and Phi-4 is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 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 $0.00 input / $0.00 output per 1M tokens for Phi-4. GPT-5.1-Codex-Max has the larger context window at 400K, compared with 16K for Phi-4.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGPT-5.1-Codex-MaxPhi-4Comparison
Input / output priceUSD per 1M tokensGPT-5.1-Codex-Max$1.25 input / $10 outputPhi-4$0 input / $0 outputPhi-4 has the lower combined listed price.
Generation speedtokens per secondGPT-5.1-Codex-MaxNot availablePhi-435 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-5.1-Codex-MaxNot availablePhi-42.02 sA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-5.1-Codex-Max400KPhi-416KGPT-5.1-Codex-Max lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGPT-5.1-Codex-MaxPhi-4Result
τ²-bench resultsSource 83%0%GPT-5.1-Codex-Max leads
Coding
BenchmarkGPT-5.1-Codex-MaxPhi-4Result
Vibe Code BenchSource 22.17%Not comparable
AA-SciCodeSource 40.2%26.0%GPT-5.1-Codex-Max leads
Reasoning
BenchmarkGPT-5.1-Codex-MaxPhi-4Result
AA-LCRSource 67.3%0.0%GPT-5.1-Codex-Max leads
CritPtSource 5.7%0.0%GPT-5.1-Codex-Max leads
Knowledge
BenchmarkGPT-5.1-Codex-MaxPhi-4Result
Artificial Analysis Intelligence IndexSource 34.7%4.9%GPT-5.1-Codex-Max leads
AA-GPQA DiamondSource 86.0%57.5%GPT-5.1-Codex-Max leads
AA-HLESource 23.4%4.1%GPT-5.1-Codex-Max leads
AA-Omniscience IndexSource -6.0%-56.7%GPT-5.1-Codex-Max leads
AA-Omniscience AccuracySource 39.2%13.2%GPT-5.1-Codex-Max leads
AA-Omniscience Hallucination RateSource 74.4%80.5%GPT-5.1-Codex-Max leads
Multimodal
BenchmarkGPT-5.1-Codex-MaxPhi-4Result
AA-MMMU-ProSource 72.5%Not comparable
Inst. Following
BenchmarkGPT-5.1-Codex-MaxPhi-4Result
AA-IFBenchSource 70.0%23.5%GPT-5.1-Codex-Max leads
Frequently Asked Questions (3)

Can I compare GPT-5.1-Codex-Max and Phi-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 Phi-4 today?

GPT-5.1-Codex-Max: $1.25 input / $10.00 output per 1M tokens Phi-4: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 24, 2026