Updated October 17, 2026. Rank says GPT-5.4 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-5.4 has the higher public point estimate, 66.7 versus 64.7. Their conditional score ranges overlap. These ranges do not establish rank confidence. 25 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Code generation, repair, and software-engineering tasks
GPT-5.4
GPT-5.4 has the higher public coding point estimate, 47.7 to 39.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
GPT-5.4
GPT-5.4 has the higher public agentic point estimate, 52.1 to 38.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
GPT-5.4
GPT-5.4 has the larger documented context window.
1K fresh input + 500 output tokens
Gemini 3.1 Pro
Gemini 3.1 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Gemini 3.1 Pro
Gemini 3.1 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Gemini 3.1 Pro
Gemini 3.1 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Like-for-like · BenchAlign v5.8
GPT-5.4 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
FrontierMath v2 (Tier 4)Math
Normalized gap 22.2FrontierMath v2 (Tiers 1-3)Math
Normalized gap 18.9HLE w/o toolsKnowledge
Normalized gap 5.6ARC-AGI-2Reasoning
Normalized gap 3.1MMMU-ProMultimodal
Normalized gap 2.7Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | Gemini 3.1 Pro | GPT-5.4 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 38.4Supported · #70/128 | 52.1Supported · #44/128 | Like-for-likeBenchAlign v5.8 lane · 7 vs 15 public rows | GPT-5.4 leads · intervals overlap |
| Coding | 39.2Supported · #67/150 | 47.7Supported · #48/150 | Like-for-likeBenchAlign v5.8 lane · 6 vs 6 public rows | GPT-5.4 leads · intervals overlap |
| Knowledge | 67.6Supported · #26/184 | 69.1Supported · #20/184 | Like-for-likeBenchAlign v5.8 lane · 6 vs 7 public rows | GPT-5.4 leads · intervals overlap |
| Multimodal | 80.1#17/54 | 73.1#30/54 | Directional onlyProvisional lane · 2 vs 3 weighted rows | Directional only |
| Reasoning | 58.2Unranked · 2 rankable rows | 64.2#23/28 | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 90.7#23/148 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 65.0Unranked · 2 rankable rows | 82.0Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 2 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
1K fresh input + 500 output tokens
Gemini 3.1 Pro has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Gemini 3.1 Pro has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Gemini 3.1 Pro has the lower modeled cost
Costs use the listed standard API rates.
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Gemini 3.1 Pro
GPT-5.4
1.05M
OpenAI pricingGemini 3.1 Pro
gemini-3.1-pro-preview
Google Gemini 3.1 Pro Preview model documentationGPT-5.4
gpt-5.4
OpenAI pricingA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Gemini 3.1 Pro
$0.2 per 1M cached input tokens
Google Gemini API pricingGPT-5.4
$0.25 per 1M cached input tokens
OpenAI pricingGemini 3.1 Pro
text, image, video, audio, pdf
Google Gemini 3.1 Pro Preview model documentationGPT-5.4
Not sourced
Gemini 3.1 Pro
GPT-5.4
Not sourced
Gemini 3.1 Pro
Preview · Gemini API, Google AI Studio
Google Gemini 3.1 Pro Preview model documentationGPT-5.4
Not sourced
Gemini 3.1 Pro
Reasoning
GPT-5.4
Reasoning
Gemini 3.1 Pro
Proprietary
GPT-5.4
Proprietary
Gemini 3.1 Pro
Proprietary
GPT-5.4
Proprietary
Gemini 3.1 Pro
2026-02-19
GPT-5.4
2026-03-05
GPT-5.4 has the higher public point estimate, 66.7 versus 64.7. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
GPT-5.4 has the higher public coding point estimate, 47.7 to 39.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
GPT-5.4 has the higher public agentic tasks point estimate, 52.1 to 38.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.008 on Gemini 3.1 Pro and $0.01 on GPT-5.4; repository review costs $0.136 and $0.17; the cache-heavy agent loop costs $0.2 and $0.25. Costs use the listed standard API rates.
GPT-5.4 has the larger documented context window: 1.05M, compared with 1M.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Claw-Eval
Shared sourceGPT-5.4 leads this result
DeepSearchQA
Shared sourceGPT-5.4 leads this result
τ²-bench results
GPT-5.4 leads this result
Gert Labs
Shared sourceGPT-5.4 leads this result
ResearchClawBench
Shared sourceGPT-5.4 leads this result
Terminal-Bench 2.1 (Vals)
Not directly comparable
MazeBench
Gemini 3.1 Pro leads this result
Terminal-Bench 2.0
Not directly comparable
CyberGym
Not directly comparable
BrowseComp
Not directly comparable
OSWorld-Verified
Not directly comparable
MCP Atlas
Not directly comparable
Toolathlon
Not directly comparable
JobBench
Not directly comparable
ExploitGym
Not directly comparable
ApprenticeBench
Not directly comparable
LiveCodeBench Pro
Shared sourceGPT-5.4 leads this result
React Native Evals
Shared sourceGPT-5.4 leads this result
Vibe Code Bench
Shared sourceGPT-5.4 leads this result
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Not directly comparable
PostTrainBench v1.1
Shared sourceGemini 3.1 Pro leads this result
SWE-bench Pro
Not directly comparable
Terminal-Bench 2.0
Not directly comparable
ARC-AGI-2
Gemini 3.1 Pro leads this result
ARC-AGI-3
Shared sourceGemini 3.1 Pro leads this result
ARC-AGI-1
Not directly comparable
MMMU-Pro
Gemini 3.1 Pro leads this result
CharXiv
Shared sourceGPT-5.4 leads this result
ERQA
Shared sourceGemini 3.1 Pro leads this result
SimpleVQA
Shared sourceGemini 3.1 Pro leads this result
ScreenSpot Pro
Shared sourceGPT-5.4 leads this result
ZeroBench
Shared sourceGPT-5.4 leads this result
MedXpertQA (MM)
Shared sourceGemini 3.1 Pro leads this result
OfficeQA Pro
Not directly comparable
MMMU-Pro w/ Python
Not directly comparable
GPQA-D
Shared sourceGemini 3.1 Pro leads this result
HLE w/o tools
Gemini 3.1 Pro leads this result
HealthBench Hard
Shared sourceGPT-5.4 leads this result
MedXpertQA (Text)
Shared sourceGemini 3.1 Pro leads this result
GPQA Diamond (Vals)
Not directly comparable
MMLU-Pro (Vals)
Not directly comparable
GPQA
Not directly comparable
HLE
Not directly comparable
HealthBench Professional
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceGPT-5.4 leads this result
FrontierMath v2 (Tier 4)
Shared sourceGPT-5.4 leads this result
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 5,600+ readers.
Last updated October 17, 2026
