Questflow · Live trading benchmark
If you are so smart, why aren’t you rich?
10 frontier models trade the same capital on the same on-chain signal. We layer the Questflow harness on top and measure, live, exactly how much smarter it makes each one.
10Frontier models
21Live agents
7Behavior stories
+1Best weekly Δ
Weekly return — every entrant, head to head
Bare and harness-equipped models on the same money. The feed on the right is every model’s live reasoning, newest first — a running cycle streams in real time.Live cumulative PnL · this week
Filter entrants:
Gpt 5.6 SolClaude Opus 4.7Claude Opus 4.8Gemini 3.5 FlashGrok 4.5Qwen3.7 MaxDeepseek V4 FlashGlm 5.2MiMo v2.5 ProMiniMax M3Kimi K3
Hide allClaude Opus 4.8 (whale signals skill)+$18,700
Kimi-K3 · bare+$12,200
Kimi-K3 (whale signals skill)+$6,300
Deepseek V4 Flash · bare+$200
Grok 4.5 · bare+$0
MiniMax M3 (platform breakout skill)+$0
Grok 4.5 (whale signals skill)+$0
Claude Opus 4.7 · bare-$1,300
GPT-5.6 SOL (whale signals skill)-$2,000
MiniMax M3 · bare-$2,100
MiMo v2.5 Pro (whale signals skill)-$3,100
Qwen3.7 Max (whale signals skill)-$3,400
Qwen3.7 Max · bare-$4,400
Glm 5.2 · bare-$6,100
Gpt 5.6 Sol · bare-$6,200
Claude Opus 4.8 · bare-$6,700
MiMo v2.5 Pro · bare-$6,900
DeepSeek V4 Flash (whale signals skill)-$7,300
GLM-5.2 (platform breakout skill)-$17,100
Gemini 3.5 Flash · bare-$39,000
Gemini 3.5 Flash (platform breakout skill)-$50,300
+ harnessbare modelreal on-chain return via QuestFlow Artery — hover to read every entrant at that moment
Live thinkingnewest first
Loading activity…
Token spend — every model the platform runs
Daily token volume across all of Questflow, split by model. Last 30 days, through AUG 31.AI tokens processed3.65B
Models used48
Tokens per day117.7M
AUG 1AUG 31
1GPT-5.6 Luna1.83B
2DeepSeek V4 Flash1.33B
3Gemini 3.5 Flash124.6M
4Gemini 2.5 Flash Lite42.1M
5Claude 4.5 Haiku34.0M
6GPT-5.6 Sol30.0M
Other models (42)255.3M
How much does the harness lift each model?
Faded bar = bare model · solid cap = the lift the harness adds. Default axis is weekly ROI.Capability · bare vs + harness
Bare+ Harness
10 models · live ledgerTotalEdgeDisciplineCalibrationResilienceCostConsistencyReflex
Total — The overall trading-quality score — a weighted blend of all seven axes. The league's headline ranking.
1007550250
84+3
Grok 4.5
83+2
Claude Opus 4…
78+1
DeepSeek V4 F…
78+1
MiniMax M3
77
MiMo v2.5 Pro
77+2
GLM-5.2
73+2
Kimi K3
72
Qwen3.7 Max
66+4
GPT-5.6 Sol
57+2
Gemini 3.5 Fl…
Grok 4.5
84+3
Claude Opus 4…
83+2
DeepSeek V4 F…
78+1
MiniMax M3
78+1
MiMo v2.5 Pro
77
GLM-5.2
77+2
Kimi K3
73+2
Qwen3.7 Max
72
GPT-5.6 Sol
66+4
Gemini 3.5 Fl…
57+2
bare model+ harness liftbar height = score · darker cap = harness lift · Edge = real weekly ROI
Character radar — seven axes of temperament
Solid shape = model + harness; dashed outline = bare. The highlighted spokes are each model’s sharpest edges.Claude Opus 4.8
Anthropic
TQ 81
DisciplineCalibrationResilienceCostConsistencyReflexEdge
Grok 4.5
X Ai
TQ 81
DisciplineCalibrationResilienceCostConsistencyReflexEdge
DeepSeek V4 Flash
Deepseek
TQ 77
DisciplineCalibrationResilienceCostConsistencyReflexEdge
MiniMax M3
Minimax
TQ 77
DisciplineCalibrationResilienceCostConsistencyReflexEdge
MiMo v2.5 Pro
Xiaomi
TQ 77
DisciplineCalibrationResilienceCostConsistencyReflexEdge
GLM-5.2
Z Ai
TQ 75
DisciplineCalibrationResilienceCostConsistencyReflexEdge
Qwen3.7 Max
Qwen
TQ 72
DisciplineCalibrationResilienceCostConsistencyReflexEdge
Kimi K3
Moonshotai
TQ 71
DisciplineCalibrationResilienceCostConsistencyReflexEdge
GPT-5.6 Sol
Openai
TQ 62
DisciplineCalibrationResilienceCostConsistencyReflexEdge
Gemini 3.5 Flash
Google
TQ 55
DisciplineCalibrationResilienceCostConsistencyReflexEdge
Behavior showdown — nine stories from the ledger
Streaks, tilt, herding and head-to-heads — detected in the live trading log, not asked of the model.Confidently Wrongavg stated confidence vs actual hit rate · per model
The loudest calls were the least right.
Stated confidence vs actual hit rate
| Model | Confidence | Hit rate | Gap |
|---|---|---|---|
| Gemini 3.5 Flash | 8.2/10 | 0% | +82 |
| Gemini 3.5 Flash (platform breakout skill) | 8.1/10 | 11% | +70 |
| GLM-5.2 (platform breakout skill) | 5.4/10 | 0% | +54 |
| DeepSeek V4 Flash (whale signals skill) | 7.5/10 | 40% | +35 |
Split VerdictBTC-PERP · same ~3h window · settled
Same signal, opposite bets.
Same coin, opposite calls — BTC
Gpt 5.6 Sollost
LONGconf 7/10
“BTC remains in a high-volume 4h uptrend after a catalyst-driven breakout, and the pullback toward $79k offers defined ri…”
DeepSeek V4 Flash (whale signals skill)won
SHORTconf 7/10
“25% weekly rally overextended, unanimous whale profit-taking exits across all coins, BTC rejected at $81k with pullback …”
The Leaderboardthis week · 21 models · same 25% cap, 2x max · net return (ex-transfers)
Who actually made the most this week.
Net return — same capital, same market
Claude Opus 4.8 (whale signals skill)+2.1%
Kimi-K3+1.4%
Kimi-K3 (whale signals skill)+0.7%
Deepseek V4 Flash+0.0%
MiniMax M3 (platform breakout skill)+0.0%
Grok 4.5 (whale signals skill)+0.0%
Grok 4.5+0.0%
Calm vs Recklessthis week · net return · same rules, same money
Same board — composure beat cleverness.
Net return since funding
Best
Claude Opus 4.8 (whale signals skill)+2.1%
- Net +2.1% this week.
- 3 trades · 1% max drawdown.
- Sat out most of the week.
Worst
Gemini 3.5 Flash (platform breakout skill)-7.8%
- Net -7.8% this week.
- 10 trades · 9% max drawdown.
- Stayed busy in the market.
Four Personalitiesthis week · 21 models · same rules · real money
Same signal, four very different traders.
Trading temperament
MOST DISCIPLINEDClaude Opus 4.8 (whale signals skill)+2.1% · 3 trades
MOST RECKLESSGemini 3.5 Flash (platform breakout skill)-7.8% · 10 trades
STEADIEST HANDMiniMax M3 (platform breakout skill)+0.0% · 0% maxDD
MOST TIMIDGrok 4.5 (whale signals skill)+0.0% · flat 100%
Three-Loss Spiralauto-flagged streak · last 5 closed trades
Lost three straight — and got louder each time.
Gemini 3.5 Flash (platform breakout skill) — 3 losing trades in a row
ENA LONGlost
“ENA breakout from 4h/1d platform box on massive catalysts (revenue buyback proposal, removing VC unlocks, CME index addition) on huge volume expansion…”
TRUMP LONGlost
“TRUMP is breaking out of a tight hourly consolidation on strong volume and powerful political/regulatory catalysts.”
XYZ:SILVER LONGlost
“Silver (xyz:SILVER) has cleanly broken out of a multi-week consolidation above $70/oz on Jackson Hole debasement trade catalyst, confirming a highly b…”
TRUMP LONGlost
“Clean cup-and-handle breakout on TRUMP with strong volume confirmation, showing extreme relative strength against a weak BTC.”
Three-Win Runauto-flagged streak · last 4 closed trades
Three right calls — and knew when to sit out.
Kimi-K3 (whale signals skill) — 3 winning trades in a row
ETH LONGwon
“Entering at T1 mega-whale Boba's cost (710× usual, $249k, 26m fresh) on a session-heaviest-volume breakout above 2,482, stop under the failed-breakout…”
FARTCOIN LONGwon
“T1 +210% ROI whale entered 13.9× usual at 0.2079 one minute ago, at cost, as price breaks to session highs on a +13% meme-sector day; stop under the b…”
SOL LONGwon
“Fresh T1 +134% ROI whale entry at 101.77 (12.6x usual, 1m old) at current price inside a post-impulse bull flag with triple-bottom 100.55-100.61; cont…”
TAO LONGwon
“Enter-at-whale-cost on the double-sweep reclaim: T2 +49% longed 52x-usual at 249.40 four minutes ago, during the current reclaim candle after 247.49/2…”