Knowledge
Like-for-like- Grok 4.3
- 57.0
- Supported · #44/183
- MiniMax M2.7
- 48.7
- Supported · #90/183
- Basis
- BenchAlign lane · 2 vs 4 public rows
- Reading
- Grok 4.3 leads · intervals overlap
Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.
Follow model changesUpdated September 10, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Grok 4.3 has the higher public score estimate, 59.73 versus 55.19, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
6 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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.
Prompts that approach the documented context limit
Grok 4.3
Grok 4.3 has the larger documented context window.
Confidence: documented
1K fresh input + 500 output tokens
MiniMax M2.7
MiniMax M2.7 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
50K fresh input + 3K output tokens
MiniMax M2.7
MiniMax M2.7 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Code generation, repair, and software-engineering tasks
Not enough matched evidence
MiniMax M2.7 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Tool use, computer use, and multi-step task completion
Not enough matched evidence
MiniMax M2.7 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Each row shows the public-lane category score for both models: the BenchAlign 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 | Grok 4.3 | MiniMax M2.7 | Basis | Reading |
|---|---|---|---|---|
| Knowledge | 57.0Supported · #44/183 | 48.7Supported · #90/183 | Like-for-likeBenchAlign lane · 2 vs 4 public rows | Grok 4.3 leads · intervals overlap |
| Agentic | 26.9Supported · #144/152 | 41.2Estimated · #111/152 | Directional onlyBenchAlign lane · 3 vs 7 public rows | Directional only |
| Coding | 33.6Supported · #131/151 | 48.7Estimated · #67/151 | Directional onlyBenchAlign lane · 2 vs 11 public rows | Directional only |
| Instruction following | 94.4#2/123 | 93.0#10/123 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Reasoning | 65.2Unranked · 2 rankable rows | 74.8Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 65.6#25/48 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
MMLU-Pro (Vals)
Knowledge
LiveCodeBench (Vals)
Coding
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
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
MiniMax M2.7 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
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.
Grok 4.3
1M
MiniMax M2.7
200K
Grok 4.3
Not sourced
MiniMax M2.7
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Grok 4.3
$0.2 per 1M cached input tokens
MiniMax M2.7
Not published
Grok 4.3
Not sourced
MiniMax M2.7
Not sourced
Grok 4.3
Not sourced
MiniMax M2.7
Not sourced
Grok 4.3
Not sourced
MiniMax M2.7
Not sourced
Grok 4.3
Reasoning
MiniMax M2.7
Non-Reasoning
Grok 4.3
Proprietary
MiniMax M2.7
Open Weight
Grok 4.3
Proprietary
MiniMax M2.7
Open Weight
Grok 4.3
2026-04-30
MiniMax M2.7
2026-03-18
Run the same representative tasks against both endpoints before changing production traffic.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Gert Labs
Shared sourceGrok 4.3 leads this result
ResearchClawBench
Not directly comparable
Terminal-Bench 2.1 (Vals)
MiniMax M2.7 leads this result
Terminal-Bench 2.0
Not directly comparable
Toolathlon
Not directly comparable
MLE-Bench Lite
Not directly comparable
MM-ClawBench
Not directly comparable
Claw-Eval
Not directly comparable
LiveCodeBench (Vals)
Grok 4.3 leads this result
SWE-bench (Vals)
MiniMax M2.7 leads this result
SWE-bench Verified*
Not directly comparable
SWE-bench Pro
Not directly comparable
SWE-Rebench
Not directly comparable
SWE Multilingual
Not directly comparable
Multi-SWE Bench
Not directly comparable
VIBE-Pro
Not directly comparable
NL2Repo
Not directly comparable
Vibe Code Bench
Not directly comparable
React Native Evals
Not directly comparable
GPQA Diamond (Vals)
Grok 4.3 leads this result
MMLU-Pro (Vals)
Grok 4.3 leads this result
GPQA-D
Not directly comparable
MMLU-Pro (Arcee)
Not directly comparable
AIME25 (Arcee)
Not directly comparable
Grok 4.3 has the higher public score estimate, 59.73 versus 55.19, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
MiniMax M2.7 scores higher for coding on the public lane, 48.7 to 33.6. MiniMax M2.7 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
MiniMax M2.7 scores higher for agentic tasks on the public lane, 41.2 to 26.9. MiniMax M2.7 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
For the stated presets, chat costs $0.0025 on Grok 4.3 and $0.0009 on MiniMax M2.7; repository review costs $0.07 and $0.0186; the cache-heavy agent loop costs $0.09 and $0.078. MiniMax M2.7 does not fit this workload in one request. MiniMax M2.7 has no published cached-input rate, so cached tokens use its listed input rate.
Grok 4.3 has the larger documented context window: 1M, compared with 200K.
Last updated September 10, 2026
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.