Noometry

Model comparison

GPT-4 Turbo vs Mercury 2.5

Mercury 2.5 is the stronger model overall, scoring 33.5 to 30.5 on the Noometry Index.

Last verified . 0 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Mercury 2.5 Inception

33.5

Rank #242 Reported

Summary

  • The widest gap is in math, where Mercury 2.5 leads 23.3 to 9.0.
  • Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Mercury 2.5 accepts more context: 260K tokens versus 128K.

Side by side

GPT-4 TurboMercury 2.5
ProviderOpenAIInception
Noometry Index30.533.5
Released2023-11-062026-09-08
WeightsProprietaryProprietary
Context window128K260K
Max output4K66K
Input $ / M tokens$10$0.04
Output $ / M tokens$30$0.15
Results tracked364

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

Category by category

Coding Mercury 2.5 leads

GPT-4 Turbo: 33.8 (#249), Mercury 2.5: 39.5 (#156)

BenchmarkGPT-4 TurboMercury 2.5
SciCode—38.5%
WeirdML18%—
BigCodeBench Instruct48.2%—
LMArena Coding1268—
BigCodeBench Complete58.2%—
ALE-Bench—301.65
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Mercury 2.5: —

BenchmarkGPT-4 TurboMercury 2.5
METR Time Horizons36.7%—

Reasoning Mercury 2.5 leads

GPT-4 Turbo: 15.3 (#317), Mercury 2.5: 22.4 (#193)

BenchmarkGPT-4 TurboMercury 2.5
SimpleBench25.1%—
CritPt—0%
Chess Puzzles6%—
LMArena Hard Prompts1251—
DTBench61.6%—
LMCA9.8%—
Epoch Capabilities Index127.25—
ForecastBench59.4—

Math Mercury 2.5 leads

GPT-4 Turbo: 9.0 (#322), Mercury 2.5: 23.3 (#272)

BenchmarkGPT-4 TurboMercury 2.5
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
ProofBench—3%
LMArena Math1272—
MATH Level 546.7%—

Knowledge Not comparable

GPT-4 Turbo: 24.3 (#268), Mercury 2.5: —

BenchmarkGPT-4 TurboMercury 2.5
GPQA Diamond46.6%—
Confabulations28.4%—
LMArena Expert1223—
MMLU81.3%—

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), Mercury 2.5: —

BenchmarkGPT-4 TurboMercury 2.5
LMArena Vision1090—

Multilingual Not comparable

GPT-4 Turbo: 40.5 (#216), Mercury 2.5: —

BenchmarkGPT-4 TurboMercury 2.5
LMArena Non-English1245—
LMArena Chinese1242—
LMArena French1276—
LMArena German1259—
LMArena Japanese1194—
LMArena Korean1187—
LMArena Russian1259—
LMArena Spanish1260—

Instruction Following Not comparable

GPT-4 Turbo: 65.8 (#216), Mercury 2.5: —

BenchmarkGPT-4 TurboMercury 2.5
LMArena Instruction Following1249—

Long Context Not comparable

GPT-4 Turbo: 38.0 (#206), Mercury 2.5: —

BenchmarkGPT-4 TurboMercury 2.5
LMArena Longer Query1254—

Writing & Preference Not comparable

GPT-4 Turbo: 47.7 (#206), Mercury 2.5: —

BenchmarkGPT-4 TurboMercury 2.5
LMArena Text1272—
LMArena Creative Writing1269—
LMArena Multi-Turn1267—

Frequently asked questions

Is GPT-4 Turbo better than Mercury 2.5?

Mercury 2.5 is the stronger model overall, scoring 33.5 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or Mercury 2.5?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Mercury 2.5 better for coding?

Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Mercury 2.5 does, with 260K tokens against 128K.

How many benchmarks do GPT-4 Turbo and Mercury 2.5 share?

0 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Mercury 2.5 has 4.

Related comparisons

Go deeper