Updated November 6, 2026. Rank says GPT-6 Luna is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-6 Luna has the higher public point estimate, 62.59 versus 55.33. Their conditional score ranges overlap. These ranges do not establish rank confidence. 2 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
MiMo-V2.6-Flash
MiMo-V2.6-Flash has the higher public coding point estimate, 56.4 to 51.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
GPT-6 Luna
GPT-6 Luna has the larger documented context window.
1K fresh input + 500 output tokens
MiMo-V2.6-Flash
MiMo-V2.6-Flash 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
MiMo-V2.6-Flash
MiMo-V2.6-Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GPT-6 Luna
GPT-6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-6 Luna and MiMo-V2.6-Flash are scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
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
MiMo-V2.6-Flash 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.
2 categories rest 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Each 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 | GPT-6 Luna | MiMo-V2.6-Flash | Basis | Reading |
|---|---|---|---|---|
| Coding | 51.8Supported · #42/157 | 56.4Supported · #28/157 | Like-for-likeBenchAlign v5.8 lane · 3 vs 3 public rows | MiMo-V2.6-Flash leads · intervals overlap |
| Agentic | 53.5Estimated · #45/131 | 48.9Estimated · #53/131 | Directional onlyBenchAlign v5.8 lane · 5 vs 9 public rows | Directional only |
| Knowledge | 63.3Supported · #40/178 | 53.0Estimated · #68/178 | Directional onlyBenchAlign v5.8 lane · 5 vs 0 public rows | Directional only |
| Reasoning | 57.5#22/25 | 74.3Unranked · 2 rankable rows | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multimodal | 81.9Unranked · 1 rankable row | 72.3Unranked · 1 rankable row | 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 |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 80.2Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 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
MiMo-V2.6-Flash has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
GPT-6 Luna has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
MiMo-V2.6-Flash 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.
GPT-6 Luna
MiMo-V2.6-Flash
GPT-6 Luna
gpt-6-luna
OpenAI GPT-6 Luna model documentationMiMo-V2.6-Flash
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-6 Luna
$0.01 per 1M cached input tokens
OpenAI GPT-6 Luna model documentationMiMo-V2.6-Flash
$0.0028 per 1M cached input tokens
Xiaomi MiMo-V2.6 launchGPT-6 Luna
text, image
OpenAI GPT-6 Luna model documentationMiMo-V2.6-Flash
Not sourced
GPT-6 Luna
MiMo-V2.6-Flash
Not sourced
GPT-6 Luna
Generally Available · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Work, Codex
OpenAI GPT-6 Sol and Luna launchMiMo-V2.6-Flash
Not sourced
GPT-6 Luna
Reasoning
MiMo-V2.6-Flash
Reasoning
GPT-6 Luna
Proprietary
MiMo-V2.6-Flash
Open Weight
GPT-6 Luna
Proprietary
MiMo-V2.6-Flash
Open Weight
GPT-6 Luna
2026-09-22
MiMo-V2.6-Flash
2026-09-22
GPT-6 Luna has the higher public point estimate, 62.59 versus 55.33. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
MiMo-V2.6-Flash has the higher public coding point estimate, 56.4 to 51.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
GPT-6 Luna scores higher for agentic tasks on the public lane, 53.5 to 48.9. GPT-6 Luna and MiMo-V2.6-Flash are 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 $0.00035 on GPT-6 Luna and $0.00028 on MiMo-V2.6-Flash; repository review costs $0.0065 and $0.00784; the cache-heavy agent loop costs $0.009 and $0.00616. Costs use the listed standard API rates.
GPT-6 Luna has the larger documented context window: 1.05M, compared with 1M.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
ExploitGym
GPT-6 Luna leads this result
Hermes Index
Not directly comparable
Hermes Bench
Not directly comparable
MazeBench
Not directly comparable
OSWorld 2.1 Offline
Not directly comparable
Toolathlon-Verified
Not directly comparable
AutomationBench
Not directly comparable
Agents' Last Exam
Not directly comparable
Terminal-Bench 4.0
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
OSWorld-Verified
Not directly comparable
JobBench
Not directly comparable
CyberGym
Not directly comparable
DeepSWE
MiMo-V2.6-Flash leads this result
Bug Hunt Bench
Not directly comparable
FrontierCode 2.0
Not directly comparable
ProgramBench
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
BioBasicsBench
Not directly comparable
ARC-AGI-1
Not directly comparable
ARC-AGI-2
Not directly comparable
ARC-AGI-3
Not directly comparable
ARC-AGI-3 Provider Adapter
Not directly comparable
HealthBench (raw)
Not directly comparable
HealthBench (length-adjusted)
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Professional (raw)
Not directly comparable
HealthBench Hard
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated November 6, 2026
