Compare · ModelsLive · 3 picked · head to head
Claude Fable 5 vs MiMo-V2.6-Pro vs Qwen3.8 Max (0902)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Fable 5 wins on 14/21 benchmarks
Claude Fable 5 wins 14 of 21 shared benchmarks. Leads in knowledge · coding · general.
Category leads
speed·MiMo-V2.6-Proarena·Qwen3.8 Max (0902)knowledge·Claude Fable 5coding·Claude Fable 5general·Claude Fable 5math·Claude Fable 5
Hype vs Reality
Attention vs performance
Claude Fable 5
#27 by perf·#12 by attention
MiMo-V2.6-Pro
no bench·no signal
Qwen3.8 Max (0902)
#102 by perf·#2 by attention
Best value
Qwen3.8 Max (0902)
5.8x better value than Claude Fable 5
Claude Fable 5
2.3 pts/$
$30.00/M
MiMo-V2.6-Pro
n/a
$0.65/M
Qwen3.8 Max (0902)
13.2 pts/$
$4.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Xiaomi (MiMo)
$111.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
21 benchmarks · 3 models
Claude Fable 5MiMo-V2.6-ProQwen3.8 Max (0902)
Artificial Analysis · Quality Index
Claude Fable 5 leads by +13.5
Claude Fable 5
59.9
MiMo-V2.6-Pro
46.3
Qwen3.8 Max (0902)
45.4
Chatbot Arena Elo · Coding
Qwen3.8 Max (0902) leads by +17.2
Claude Fable 5
1653.9
MiMo-V2.6-Pro
1618.4
Qwen3.8 Max (0902)
1671.2
Chatbot Arena Elo · Overall
Claude Fable 5 leads by +26.0
Claude Fable 5
1507.6
MiMo-V2.6-Pro
1480.1
Qwen3.8 Max (0902)
1481.6
Artificial Analysis · CritPt
MiMo-V2.6-Pro leads by +8.9
MiMo-V2.6-Pro
26.6
Qwen3.8 Max (0902)
17.7
Artificial Analysis · GDPval
MiMo-V2.6-Pro leads by +0.7
MiMo-V2.6-Pro
59.3
Qwen3.8 Max (0902)
58.6
Artificial Analysis · Humanity's Last Exam
MiMo-V2.6-Pro leads by +6.3
MiMo-V2.6-Pro
49.4
Qwen3.8 Max (0902)
43.1
Artificial Analysis · Long Context Reasoning
MiMo-V2.6-Pro leads by +6.0
MiMo-V2.6-Pro
86.3
Qwen3.8 Max (0902)
80.3
Artificial Analysis · SciCode
MiMo-V2.6-Pro leads by +8.8
MiMo-V2.6-Pro
60.9
Qwen3.8 Max (0902)
52.1
Chess Puzzles
Claude Fable 5 leads by +12.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Fable 5
37.9
Qwen3.8 Max (0902)
25.3
Deepswe
Claude Fable 5 leads by +12.4
Claude Fable 5
69.9
Qwen3.8 Max (0902)
57.5
Dtbench
Claude Fable 5 leads by +10.7
Claude Fable 5
97.3
Qwen3.8 Max (0902)
86.7
FrontierMath-Tier-4-v2-Private
Claude Fable 5 leads by +43.9
Claude Fable 5
90.2
Qwen3.8 Max (0902)
46.3
FrontierMath-Tiers-1-3-v2-Private
Claude Fable 5 leads by +12.3
Claude Fable 5
87.0
Qwen3.8 Max (0902)
74.7
Frontierswe
Claude Fable 5 leads by +31.1
Claude Fable 5
47.0
Qwen3.8 Max (0902)
15.8
Furniture Assembly
Claude Fable 5 leads by +8.3
Claude Fable 5
8.3
Qwen3.8 Max (0902)
0.0
GPQA diamond
Qwen3.8 Max (0902) leads by +9.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Fable 5
81.1
Qwen3.8 Max (0902)
90.2
Lmca
Claude Fable 5 leads by +17.5
Claude Fable 5
71.9
Qwen3.8 Max (0902)
54.4
Mystery Game Puzzles
Claude Fable 5 leads by +15.4
Claude Fable 5
47.1
Qwen3.8 Max (0902)
31.7
OTIS Mock AIME 2024-2025
Claude Fable 5 leads by +0.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Fable 5
100.0
Qwen3.8 Max (0902)
99.4
Proofbench
Claude Fable 5 leads by +37.0
Claude Fable 5
95.0
Qwen3.8 Max (0902)
58.0
SimpleQA Verified
Claude Fable 5 leads by +24.9
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Fable 5
70.7
Qwen3.8 Max (0902)
45.8
Full benchmark table
| Benchmark | Claude Fable 5 | MiMo-V2.6-Pro | Qwen3.8 Max (0902) |
|---|---|---|---|
Artificial Analysis · Quality Index | 59.9 | 46.3 | 45.4 |
Chatbot Arena Elo · Coding | 1653.9 | 1618.4 | 1671.2 |
Chatbot Arena Elo · Overall | 1507.6 | 1480.1 | 1481.6 |
Artificial Analysis · CritPt | — | 26.6 | 17.7 |
Artificial Analysis · GDPval | — | 59.3 | 58.6 |
Artificial Analysis · Humanity's Last Exam | — | 49.4 | 43.1 |
Artificial Analysis · Long Context Reasoning | — | 86.3 | 80.3 |
Artificial Analysis · SciCode | — | 60.9 | 52.1 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 37.9 | — | 25.3 |
Deepswe | 69.9 | — | 57.5 |
Dtbench | 97.3 | — | 86.7 |
FrontierMath-Tier-4-v2-Private | 90.2 | — | 46.3 |
FrontierMath-Tiers-1-3-v2-Private | 87.0 | — | 74.7 |
Frontierswe | 47.0 | — | 15.8 |
Furniture Assembly | 8.3 | — | 0.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 81.1 | — | 90.2 |
Lmca | 71.9 | — | 54.4 |
Mystery Game Puzzles | 47.1 | — | 31.7 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 100.0 | — | 99.4 |
Proofbench | 95.0 | — | 58.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 70.7 | — | 45.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $10.00 | $50.00 | 1.0M tokens (~500 books) | $200.00 | |
| $0.43 | $0.87 | 1.1M tokens (~525 books) | $5.44 | |
| $2.00 | $6.00 | 1.0M tokens (~500 books) | $30.00 |