Noometry

Model comparison

Claude Opus 4.5 vs MiMo-V2.6-Flash

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 48.5 on the Noometry Index. MiMo-V2.6-Flash costs 57× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 16 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

MiMo-V2.6-Flash Xiaomi

48.5

Rank #55 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude Opus 4.5 scores higher in 7 categories and MiMo-V2.6-Flash in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude Opus 4.5 leads 56.5 to 42.2.
  • The biggest single-benchmark swing is ProofBench: 36% for Claude Opus 4.5 and 63% for MiMo-V2.6-Flash.
  • MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 200K.
  • MiMo-V2.6-Flash has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.5MiMo-V2.6-Flash
ProviderAnthropicXiaomi
Noometry Index50.548.5
Released2025-11-012026-09-21
WeightsProprietaryOpen
Context window200K1.05M
Max output64K131K
Input $ / M tokens$5$0.14
Output $ / M tokens$25$0.28
Results tracked6919

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 54.8 (#27), MiMo-V2.6-Flash: 53.4 (#30)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena WebDev14941637
LMArena Coding15041504
SWE-bench Verified76.7%—
SWE-bench Verified (bash only)76.8%—
SWE-bench Multilingual70.7%—
SciCode—51.3%
GSO26.5%—
WeirdML63.7%—
ALE-Bench1,025—
AlgoTune1.77—

Agentic & Tool Use Not comparable

Claude Opus 4.5: 47.3 (#12), MiMo-V2.6-Flash: —

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
Terminal-Bench63.1%—
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
LMArena Search1180—
METR Time Horizons75%—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), MiMo-V2.6-Flash: 36.5 (#66)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena Hard Prompts14761482
ARC-AGI-237.6%—
SimpleBench62%—
Kagi LLM Benchmark80.2%—
NYT Connections (extended)52.5%—
ARC-AGI-180%—
CritPt—12%
Chess Puzzles12%—
EnigmaEval11.9%—
EBR-Bench14.3%—
Mystery Game Puzzles22%—
DTBench89.9%—
LMCA44.5%—
Epoch Capabilities Index150.09—
ForecastBench60.7—

Math MiMo-V2.6-Flash leads

Claude Opus 4.5: 38.6 (#132), MiMo-V2.6-Flash: 51.9 (#52)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
ProofBench36%63%
LMArena Math14631468
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—
OTIS Mock AIME 2024-202586.1%—
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), MiMo-V2.6-Flash: 42.2 (#99)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena Expert14871501
GPQA Diamond86%—
Humanity's Last Exam25.2%—
SimpleQA Verified45.7%—
Vectara Hallucination Rate10.9%—

Multimodal MiMo-V2.6-Flash leads

Claude Opus 4.5: 31.4 (#107), MiMo-V2.6-Flash: 40.5 (#47)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena Vision—1259
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—
LMArena Document1462—

Multilingual Too close to call

Claude Opus 4.5: 54.3 (#47), MiMo-V2.6-Flash: 54.0 (#51)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena Non-English14381434
LMArena Chinese14701511
LMArena French14711475
LMArena Russian14471409
LMArena Spanish14581456
LMArena German1449—
LMArena Japanese1416—
LMArena Korean1424—

Instruction Following Too close to call

Claude Opus 4.5: 77.5 (#19), MiMo-V2.6-Flash: 76.8 (#35)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena Instruction Following14781463

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), MiMo-V2.6-Flash: 44.8 (#57)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena Longer Query14801463
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), MiMo-V2.6-Flash: 63.1 (#67)

BenchmarkClaude Opus 4.5MiMo-V2.6-Flash
LMArena Text14511455
LMArena Creative Writing14451400
LMArena Multi-Turn14661451
EQ-Bench Creative Writing1687—

Frequently asked questions

Is Claude Opus 4.5 better than MiMo-V2.6-Flash?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 48.5 on the Noometry Index. MiMo-V2.6-Flash costs 57× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.5 or MiMo-V2.6-Flash?

MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or MiMo-V2.6-Flash better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 53.4 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.6-Flash does, with 1.05M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and MiMo-V2.6-Flash share?

16 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and MiMo-V2.6-Flash has 19.

Related comparisons

Go deeper