Xing4.0-29B-A4B
- Input
- —
- Output
- —
- Speed
- ~110tok/sest.
- Context
- 262Ktokens
Released Sep 17, 2026 per the official GitHub announcement (https://github.com/XingChen-AGI/Xing4.0-29B-A4B#news). Apache-2.0 MoE, formerly the TeleChat series; native 256K context, extensible to 512K. Parameter counts follow the developer's model card. MTP supports speculative decoding; no separate official draft model was found as of Sep 26. No measured API price or speed found. Terminal-Bench 2.1 and Tau3-Bench scores are not mapped to the site's Terminal-Bench 4.0 and tau3-Banking benchmarks.
Rankings
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.
- Hardware
- 1× B200 180GB
- BF16 weights
- Throughput
- ~10,211 tok/s
- many requests batched
- Price
- $0.067–0.60 /M tok
- busy → light use
- On your own machine
- RTX 5090 32GB (int4, 300+ tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- BF16 weights (29B params, 4B active per token) + 25% KV-cache headroom ≈ 73 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~10,211 output tok/s aggregate at batch 256 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~132,891 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench Pro (Public)Estimated
~#16 of 24 (estimated)~58.4%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #15GPT-5.558.6%
- ~#16Xing4.0-29B-A4BEstimated58.4%
- #16Hy357.9%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#41 of 46 (estimated)~41.7%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #40Qwen3.8 27B42.2%
- ~#41Xing4.0-29B-A4BEstimated41.7%
- #41Laguna S 2.140.4%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#24 of 102 (estimated)~29.1%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #22GLM-5.3 Flash32.8%
- ~#24Xing4.0-29B-A4BEstimated29.1%
- #24DeepSeek V4.1 Flash26.8%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#10 of 28 (estimated)~86.3%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #9Nemotron 3.5 Super VL NVFP487.4%
- ~#10Xing4.0-29B-A4BEstimated86.3%
- #10Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
SciCodeEstimated
~#27 of 119 (estimated)~55.7%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #26GPT-6.1 Sol55.7%
- ~#27Xing4.0-29B-A4BEstimated55.7%
- #27Claude Haiku 5.555.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#8 of 26 (estimated)~54.5
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #7GPT-6 Astra54.7
- ~#8Xing4.0-29B-A4BEstimated54.5
- #8GPT-6.1 Sol54.1
No published score — estimated from related benchmarks
Writing & chat
IFBenchLab-reported
#38 of 13969.7%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #37Nova 2.0 Lite70.7%
- #38Xing4.0-29B-A4B69.7%
- #39Apriel-v1.6-15B-Thinker69.1%
huggingface.co · 2026-09-17
LMArena Text, Non-English (Elo)Estimated
~#28 of 57 (estimated)~1434 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #27GPT-6 Luna1436
- ~#28Xing4.0-29B-A4BEstimated1434
- #28Qwen3.5 397B A17B1434
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#27 of 57 (estimated)~1447 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #26GPT-5.4 mini1448
- ~#27Xing4.0-29B-A4BEstimated1447
- #27Step 5 Preview1447
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1936 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #8Grok 4.72007
- ~#9Xing4.0-29B-A4BEstimated1936
- #9Muse Spark 1.31906
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondEstimated
~#73 of 193 (estimated)~82.0%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #72K2 Horizon MoVA 36B A4B82.2%
- ~#73Xing4.0-29B-A4BEstimated82.0%
- #73GPT-5.4 nano81.7%
No published score — estimated from related benchmarks
Humanity's Last ExamEstimated
~#64 of 199 (estimated)~27.9%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #63GPT-5.4 mini28.1%
- ~#64Xing4.0-29B-A4BEstimated27.9%
- #64MiMo-V2.527.2%
No published score — estimated from related benchmarks
AIME (latest)Lab-reported
#11 of 3390.0%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #10GLM-5.3-MXFP491.3%
- #11Xing4.0-29B-A4B90.0%
- #12gpt-oss-20b89.3%
huggingface.co · 2026-09-17
AA Intelligence IndexEstimated
~#40 of 103 (estimated)~29.6
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #39Gemini 3.1 Pro29.7
- ~#40Xing4.0-29B-A4BEstimated29.6
- #40MiniMax-M329.2
No published score — estimated from related benchmarks