Is Qwen3 235B A22B Thinking 2507 a good deal?

Whether anything in this catalogue beats Qwen3 235B A22B Thinking 2507 on both quality and price, and what you give up if it does. A computation on the current catalogue, not an opinion.

12 undominated of 144 · Nov 22, 2026

As of Nov 22, 2026, Qwen3 235B A22B Thinking 2507 is dominated for Balanced on LMArena. MiMo-V2.6-Pro scores 77.3 higher and costs 55% less, with a covering envelope. 12 of 144 rated, priced standard models are undominated.

Inspect model evidence Compare differences & requirements

Current model

Qwen3 235B A22B Thinking 2507

Balanced

3 tokens in per 1 out

MiMo-V2.6-Pro is both better and cheaper than Qwen3 235B A22B Thinking 2507: 77.3 points higher on LMArena and 55% less per million tokens, $0.673 cheaper at this mix.

Qwen3 235B A22B Thinking 2507

LMArena Elo · higher is better

Scale starts at 1040 Elo

1415.4

Effective $/M · Balanced · lower is better

$1.21/M

MiMo-V2.6-Pro

LMArena Elo · higher is better

Scale starts at 1040 Elo

1492.7

Effective $/M · Balanced · lower is better

$0.540/M

Qwen3 235B A22B Thinking 2507 takes text, returns up to 16,384 tokens from a 128,000-token context, and is listed by 1 seller.

Compared against 144 rated, priced models on this lens: 34 models dominate it and give up nothing, 3 more dominate it but give something up. Qwen3 235B A22B Thinking 2507 scores 1415.4 at $1.21 per million tokens for this mix.

Envelope-safe replacements

Each row scores at least as high, costs no more, and covers this model’s context, output, modalities, tools, and reasoning. A cheaper narrower model is not listed here.

ModelLMArenaEffective $/MYou save
MiMo-V2.6-Pro1492.7 +77.3$0.540/M55%
GLM 5.31475.4 +60.0$1.000/M18%
GLM 5.3 Flash1471.4 +56.0$0.148/M88%
GLM 5.21469.5 +54.1$0.977/M19%
MiMo-V2.5-Pro1463.9 +48.5$0.810/M33%
DeepSeek V4.1 Flash1463.0 +47.6$0.227/M81%
Qwen3.7 Plus1454.1 +38.7$0.560/M54%
MiMo-V2.6-Flash1449.8 +34.4$0.175/M86%
GLM 51446.1 +30.7$1.09/M11%
DeepSeek V4 Pro 04231444.7 +29.3$1.10/M9%
Kimi K2.51444.7 +29.3$1.20/M1%
Gemma 4 31B1442.5 +27.1$0.205/M83%
GLM 4.61440.3 +24.9$0.760/M37%
Hy31439.0 +23.6$0.231/M81%
Qwen3.5 397B A17B1437.6 +22.2$0.878/M28%
Qwen3.8 27B1437.4 +22.0$0.956/M21%
Qwen3.6 Plus1436.2 +20.8$0.731/M40%
GLM 4.71435.4 +20.0$0.738/M39%
Gemini 3.5 Flash Lite1435.0 +19.6$0.850/M30%
Gemma 4 26B A4B 1434.2 +18.8$0.123/M90%
DeepSeek V4 Flash 04231431.9 +16.5$0.113/M91%
GPT-5.6 Luna1430.9 +15.5$0.450/M63%
GLM 4.51430.2 +14.8$1.00/M18%
MiMo-V2.51427.7 +12.3$0.800/M34%
R1 05281427.7 +12.3$0.920/M24%
MiniMax M31426.5 +11.1$0.525/M57%
DeepSeek V3.21424.6 +9.2$0.394/M67%
Beam 1.0 501B A23B1424.3 +8.9$0.600/M51%
DeepSeek V3.2 Exp1422.3 +6.9$0.305/M75%
DeepSeek V3.11419.8 +4.4$0.453/M63%
Qwen3.5-122B-A10B1417.5 +2.1$0.715/M41%
DeepSeek V3.1 Terminus1417.3 +1.9$0.453/M63%
Gemini 2.5 Flash1416.9 +1.5$0.850/M30%
Gemini 3.1 Flash Lite Preview1416.2 +0.8$0.563/M54%

Higher score, lower price, named losses

Not a drop-in. The loss is why these are not a recommendation.

ModelLMArenaEffective $/MYou give up
Qwen3 VL 235B A22B Instruct1420.0$0.370/Mreasoning
Qwen3 235B A22B Instruct 25071419.2$0.205/Mreasoning
Qwen3 Next 80B A3B Instruct1417.2$0.343/Mreasoning
MiMo-V2.6-Pro1492.7 · $0.540/MQwen3 235B A22B Thinking 25071415.4 · $1.21/MLMArena EloEffective $/M · Balanced
144 rated, priced standard models. Chartreuse is the frontier. Cobalt is the model you named, when it is not on the staircase.

Open the frontier

The link keeps the model and mix, using the current catalogue. Monthly spend and switching cost stay in this browser tab and are left out of the link.

Saved decision references

Save the model, workload, catalogue date and capability-preservation rule in this browser. Spend, switching cost and bill contents are not saved. No account or notifications.

Constraint: replacements must preserve the model’s capabilities; any losses remain named trade-offs.

Historical decisions cannot be fully replayed from saved references: past prices, scores and capability evidence are not stored.

Evidence & Ask