Updated November 10, 2026. Rank says Grok 4.6 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Grok 4.6 has the higher public point estimate, 66.47 versus 64.26. Their conditional score ranges overlap. These ranges do not establish rank confidence. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Gemini 3.1 Pro: $2 input / $12 output
Grok 4.6: $2 input / $6 output
Gemini 3.1 Pro: 1M
Grok 4.6: 500K
Gemini 3.1 Pro: February 19, 2026
Grok 4.6: August 12, 2026
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
Grok 4.6
Grok 4.6 has the higher public coding point estimate, 58.6 to 39.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
Grok 4.6
Grok 4.6 has the higher public agentic point estimate, 69.7 to 40.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
Gemini 3.1 Pro
Gemini 3.1 Pro has the larger documented context window.
1K fresh input + 500 output tokens
Grok 4.6
Grok 4.6 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Grok 4.6
Grok 4.6 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
No clear pick
A complete comparable API-rate estimate is not available for both models.
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
Grok 4.6 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.
The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
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.
ARC-AGI-2Reasoning
Normalized gap 10.0FrontierMath v2 (Tiers 1-3)Math
Normalized gap 6.3FrontierMath v2 (Tier 4)Math
Normalized gap 4.9ARC-AGI-3Reasoning
Normalized gap 1.7MMLU-Pro (Vals)Knowledge
Normalized gap 1.6Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, 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 | Grok 4.6 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 40.8Supported · #70/132 | 69.7Supported · #11/132 | Like-for-likeBenchAlign v5.8 lane · 7 vs 7 public rows | Grok 4.6 leads |
| Coding | 39.4Supported · #75/158 | 58.6Supported · #23/158 | Like-for-likeBenchAlign v5.8 lane · 7 vs 9 public rows | Grok 4.6 leads |
| Knowledge | 66.6Supported · #25/179 | 67.9Supported · #21/179 | Like-for-likeBenchAlign v5.8 lane · 6 vs 2 public rows | Grok 4.6 leads · intervals overlap |
| Reasoning | 57.0Estimated · #41/158 | 65.0Supported · #22/158 | Directional onlyBenchAlign v5.8 lane · 2 vs 3 public rows | Directional only |
| Multimodal | 65.7Estimated · #22/67 | Not ranked | Not comparableBenchAlign v5.8 lane · 8 vs 0 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 90.2#27/157 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 60.6Unranked · 2 rankable rows | 65.6Unranked · 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, reasoning, multimodal, 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
Grok 4.6 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Grok 4.6 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Modeled costs are equal
Costs use the listed standard API rates.
Enter a month of tokens to price it at both models’ listed API rates.
Standard listed rates, no batch or volume discounts.
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
Grok 4.6
Gemini 3.1 Pro
gemini-3.1-pro-preview
Google Gemini 3.1 Pro Preview model documentationGrok 4.6
grok-4.6
xAI Grok 4.6 release notesA 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 pricingGrok 4.6
$0.5 per 1M cached input tokens
xAI Grok 4.6 release notesGemini 3.1 Pro
text, image, video, audio, pdf
Google Gemini 3.1 Pro Preview model documentationGrok 4.6
text, image
xAI model page for grok-4.6Gemini 3.1 Pro
Grok 4.6
Gemini 3.1 Pro
Preview · Gemini API, Google AI Studio
Google Gemini 3.1 Pro Preview model documentationGrok 4.6
Not sourced
Gemini 3.1 Pro
Reasoning
Grok 4.6
Reasoning
Gemini 3.1 Pro
Proprietary
Grok 4.6
Proprietary
Gemini 3.1 Pro
Proprietary
Grok 4.6
Proprietary
Gemini 3.1 Pro
2026-02-19
Grok 4.6
2026-08-12
Grok 4.6 has the higher public point estimate, 66.47 versus 64.26. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Grok 4.6 has the higher public coding point estimate, 58.6 to 39.4, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Grok 4.6 has the higher public agentic tasks point estimate, 69.7 to 40.8, 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 $0.005 on Grok 4.6; repository review costs $0.136 and $0.118; the cache-heavy agent loop costs $0.2 and $0.2. Costs use the listed standard API rates.
Gemini 3.1 Pro has the larger documented context window: 1M, compared with 500K.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Claw-Eval
Not directly comparable
DeepSearchQA
Not directly comparable
τ²-bench results
Not directly comparable
Gert Labs
Not directly comparable
ResearchClawBench
Not directly comparable
Terminal-Bench 2.1 (Vals)
Grok 4.6 leads this result
MazeBench
Tie
Terminal-Bench 4.1
Not directly comparable
Terminal-Bench 3.0
Not directly comparable
APEX-Agents
Not directly comparable
ApprenticeBench
Not directly comparable
CWE-bench v1
Not directly comparable
ScarfBench
Not directly comparable
LiveCodeBench Pro
Not directly comparable
React Native Evals
Not directly comparable
Vibe Code Bench
Not directly comparable
LiveCodeBench (Vals)
Gemini 3.1 Pro leads this result
SWE-bench (Vals)
Grok 4.6 leads this result
PostTrainBench v1.1
Not directly comparable
Bug Hunt Bench
Not directly comparable
DeepSWE
Not directly comparable
CursorBench 3.2
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
VulcanBench v3
Not directly comparable
FrontierSWE v2
Not directly comparable
CursorBench 4.0
Not directly comparable
ParseBench
Not directly comparable
MMMU-Pro
Not directly comparable
CharXiv
Not directly comparable
ERQA
Not directly comparable
SimpleVQA
Not directly comparable
ScreenSpot Pro
Not directly comparable
ZeroBench
Not directly comparable
MedXpertQA (MM)
Not directly comparable
GPQA-D
Not directly comparable
HLE w/o tools
Not directly comparable
HealthBench Hard
Not directly comparable
MedXpertQA (Text)
Not directly comparable
GPQA Diamond (Vals)
Gemini 3.1 Pro leads this result
MMLU-Pro (Vals)
Gemini 3.1 Pro leads this result
Gray Swan IPI (15 attempts)
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceGrok 4.6 leads this result
FrontierMath v2 (Tier 4)
Shared sourceGrok 4.6 leads this result
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 7,000+ subscribers.
Last updated November 10, 2026
